{"id":72,"date":"2020-09-03T16:39:12","date_gmt":"2020-09-03T13:39:12","guid":{"rendered":"http:\/\/acikkitap.com.tr\/oaek\/chapter\/bolum-14-oa-ve-evmde-verilere-dayali-ogrenci-geri-bildirimi-saglama\/"},"modified":"2020-09-03T16:39:12","modified_gmt":"2020-09-03T13:39:12","slug":"bolum-14-oa-ve-evmde-verilere-dayali-ogrenci-geri-bildirimi-saglama","status":"publish","type":"chapter","link":"https:\/\/acikkitap.com.tr\/oaek\/chapter\/bolum-14-oa-ve-evmde-verilere-dayali-ogrenci-geri-bildirimi-saglama\/","title":{"raw":"B\u00f6l\u00fcm 14 \u00d6A ve EVM'de Verilere Dayal\u0131 \u00d6\u011frenci Geri Bildirimi Sa\u011flama","rendered":"B\u00f6l\u00fcm 14 \u00d6A ve EVM’de Verilere Dayal\u0131 \u00d6\u011frenci Geri Bildirimi Sa\u011flama"},"content":{"raw":"\n

<\/a> Abelardo Pardo 1<\/sup>, Oleksandra Poquet 2<\/sup>, Roberto Martfnez \u2013 Maidonado 3<\/sup>, Shane Dawson2<\/sup><\/span><\/span><\/p>\n

1<\/sup> Bilgi \u0130leti\u015fim ve M\u00fchendislik Fak\u00fcltesi, Sidney \u00dcniversitesi,Avustralya<\/span><\/span><\/p>\n

2<\/sup>\u00d6\u011fretim \u0130novasyon Birimi, G\u00fcney Avustralya \u00dcniversitesi, Avustralya<\/span><\/span><\/p>\n

3<\/sup>Ba\u011flant\u0131sal Zek\u00e2 Merkezi, Teknoloji \u00dcniversitesi Sydney, Avustralya<\/span><\/span><\/p>\n

DOI: 10.18608\/hla17.014<\/span><\/span><\/p>\n\n

\u00d6Z<\/h2>\n

\u00d6\u011frenme analiti\u011fi (\u00d6A) ve e\u011fitsel veri madencili\u011fi (EVM) alanlar\u0131, \u00f6\u011frenme ortamlar\u0131 hakk\u0131ndaki bilgileri geli\u015ftirmek ve \u00f6\u011frencilerin genel deneyim kalitesini art\u0131rmak i\u00e7in verilerin kullan\u0131m\u0131n\u0131 ara\u015ft\u0131rmaktad\u0131r. Her iki disiplinin odak noktas\u0131, \u00f6\u011fretim tasar\u0131m\u0131, \u00f6zel ders verme, \u00f6\u011frenen ba\u015far\u0131s\u0131, duygusal esenlik vb. \u0130le ilgili geni\u015f bir yelpazeyi kapsar. Bu b\u00f6l\u00fcm, bu disiplinlerden elde edilen bilgileri, \u00f6\u011frencilere geri bildirim sa\u011flama konusundaki mevcut ara\u015ft\u0131rmalar ile birle\u015ftirme potansiyeline odaklanmaktad\u0131r. Geribildirim, bir \u00f6\u011frenme senaryosunda \u00f6nemli iyile\u015ftirme sa\u011flayabilecek fakt\u00f6rlerden biri olarak tan\u0131mlanm\u0131\u015ft\u0131r. Geri bildirimi karakterize eden sa\u011flam bir \u00e7al\u0131\u015fma toplulu\u011fu olmas\u0131na ra\u011fmen, \u00f6\u011frenenler hakk\u0131ndaki her yerde bulunan verilerin varl\u0131\u011f\u0131 ile bir araya gelmek, yeni veri odakl\u0131 \u00f6\u011frenen destek eylemlerini ke\u015ffetmek i\u00e7in verimli bir zemin sunar.<\/span><\/span><\/p>\n

Anahtar Kelimeler<\/span>: Uygulanabilir bilgi, geri bildirim, m\u00fcdahaleler, \u00f6\u011frenen destek eylemleri<\/span><\/span><\/p>\n

Son yirmi y\u0131l boyunca, e\u011fitim uygulamas\u0131 bir\u00e7ok cephede \u00f6nemli \u00f6l\u00e7\u00fcde de\u011fi\u015fmi\u015ftir. Buna e\u011fitim politikas\u0131ndaki de\u011fi\u015fimler de d\u00e2hildir, teknoloji zengini \u00f6\u011frenme alanlar\u0131n\u0131n ortaya \u00e7\u0131k\u0131\u015f\u0131, \u00f6\u011frenme teorisindeki geli\u015fmeler ve kalite g\u00fcvencesi ve de\u011ferlendirmesinin uygulanmas\u0131, bunlardan birka\u00e7\u0131d\u0131r. Bu de\u011fi\u015fikliklerin t\u00fcm\u00fc, \u00e7a\u011fda\u015f \u00f6\u011fretim uygulamas\u0131n\u0131n \u015fimdi nas\u0131l uyguland\u0131\u011f\u0131n\u0131 ve somutla\u015ft\u0131r\u0131ld\u0131\u011f\u0131n\u0131 etkilemi\u015ftir. E\u011fitim alan\u0131ndaki \u00e7ok say\u0131da paradigma kaymas\u0131na ra\u011fmen, \u00f6\u011frenenin \u00f6\u011frenmesini te\u015fvik etmede geri bildirimin kilit rol\u00fc, etkili \u00f6\u011fretim olarak kabul edilenler i\u00e7in temel olmaya devam etmi\u015ftir. Ayr\u0131ca, e\u011fitimin kitleselle\u015fmesiyle hem \u00f6\u011fretmenlere hem de \u00f6\u011frenenlere ger\u00e7ek zamanl\u0131 geri bildirim ve eyleme ge\u00e7irilebilir i\u00e7g\u00f6r\u00fcler sa\u011flama ihtiyac\u0131 giderek daha da artmaktad\u0131r. E\u011fitim dijital teknolojileri benimsedi\u011finden, bu t\u00fcr teknolojilerin kullan\u0131lmas\u0131n\u0131n \u00f6\u011frenenin \u00f6\u011frenmesine daha fazla yard\u0131mc\u0131 olaca\u011f\u0131, onlar\u0131 te\u015fvik edece\u011fi ve sosyo-k\u00fclt\u00fcrel ve ekonomik e\u015fitsizlikleri ele alaca\u011f\u0131na ili\u015fkin yayg\u0131n bir varsay\u0131m vard\u0131r. Bu pozitivist ideal, daha ki\u015fiselle\u015ftirilmi\u015f ve uyarlanabilir \u00f6\u011frenme yollar\u0131 olu\u015ftururken, e\u011fitime eri\u015filebilirli\u011fi art\u0131rmak i\u00e7in teknolojilerin benimsenebilece\u011fi fikrini yans\u0131tmaktad\u0131r.<\/span><\/p>\n

Bu ba\u011flamda, \u00f6\u011frenme analiti\u011fi (\u00d6A) ve e\u011fitsel veri madencili\u011fi (EVM) alanlar\u0131 e\u011fitim ile do\u011frudan ili\u015fkilidir. \u00d6A ve EVM, daha etkili \u00f6\u011fretim uygulamalar\u0131 geli\u015ftirmek i\u00e7in \u00f6\u011frenme s\u00fcre\u00e7lerini daha iyi anlamay\u0131 ama\u00e7lamaktad\u0131r (Baker ve Siemens, 2014). \u00d6\u011frencinin ilerlemesi hakk\u0131nda geri bildirim sa\u011flamak i\u00e7in \u00e7e\u015fitli teknolojilerle \u00f6\u011frenen etkile\u015fimlerinden geli\u015fen verilerin analizi, \u00d6A ve EVM \u00e7al\u0131\u015fmalar\u0131n\u0131n merkezinde yer alm\u0131\u015ft\u0131r. Bu b\u00f6l\u00fcmde, geri bildirimin \u00f6\u011frenenin \u00f6\u011frenmesini etkileyen en g\u00fc\u00e7l\u00fc itici g\u00fc\u00e7lerden biri oldu\u011funu savunuyoruz. Bu nedenle, \u00f6\u011frenme deneyiminin genel kalitesi, bir \u00f6\u011frenenin ald\u0131\u011f\u0131 geri bildirimin uygunlu\u011fu ve belirginli\u011fi ile derinden i\u00e7 i\u00e7edir. Ayr\u0131ca, geri bildirim sa\u011flama, de\u011ferlendirme yakla\u015f\u0131mlar\u0131 (Boud, 2000), \u00f6\u011frenme tasar\u0131m\u0131 (Lockyer, Heathcote ve Dawson, 2013) veya \u00f6\u011frenenlerin \u00f6z y\u00f6netimini te\u015fvik etme stratejileri gibi bir \u00f6\u011frenme deneyiminin di\u011fer y\u00f6nleriyle yak\u0131ndan ilgilidir. (Winne, 2014; Winne ve Baker, 2013). Bu b\u00f6l\u00fcmdeki tart\u0131\u015fman\u0131n \u00e7o\u011funlu\u011fu t\u00fcm e\u011fitim alanlar\u0131na uygulanabilse de inceleme a\u011f\u0131rl\u0131kl\u0131 olarak orta\u00f6\u011fretim sonras\u0131 e\u011fitim ve mesleki geli\u015fim \u00fczerine odaklanmaktad\u0131r.<\/span><\/p>\n\n

\u00d6\u011eRENMEDE VER\u0130 G\u00dcD\u00dcML\u00dc GER\u0130 B\u0130LD\u0130R\u0130M\u0130N ROL\u00dc<\/h2>\n

Geri bildirim ile ilgili tart\u0131\u015fmalar genellikle bir de\u011ferlendirme ve \u00f6\u011frenen ba\u015far\u0131s\u0131 etraf\u0131nda ger\u00e7ekle\u015fir (Black ve Wiliam, 1998; Boud, 2000). Bu ba\u011flamda, geri bildirimin birincil rol\u00fc, \u00f6\u011frenenin bir de\u011ferlendirme maddesinin tamamlanmas\u0131yla tespit edilen (alg\u0131lanan) a\u00e7\u0131klar\u0131 gidermesine yard\u0131mc\u0131 olmakt\u0131r. \u0130ronik olarak, de\u011ferlendirme puanlar\u0131 ve \u00f6\u011frenci ba\u015far\u0131s\u0131 verileri ayn\u0131 zamanda politik \u00f6ncelikleri ve g\u00fcndemleri y\u00f6nlendirmek i\u00e7in bir ara\u00e7 haline gelmi\u015ftir ve ayn\u0131 zamanda kalite g\u00fcvence \u015fartlar\u0131nda g\u00f6stergeler olarak kullan\u0131lmaktad\u0131r. \u00d6z\u00fcnde de\u011ferlendirme, kalite g\u00fcvencesini \u00f6l\u00e7mek ve rekabet\u00e7i s\u0131ralamalar\u0131 olu\u015fturmak i\u00e7in bir ara\u00e7 oldu\u011fu kadar, \u00f6\u011frenmeyi te\u015fvik etmek i\u00e7in kullan\u0131lan iki ucu keskin bir b\u0131\u00e7akt\u0131r (Wiliam, Lee, Harrison ve Black, 2004). Kalite g\u00fcvencesi i\u00e7in de\u011ferlendirmenin \u00f6nemini kabul ederken, \u00f6zellikle bi\u00e7imlendirici de\u011ferlendirme ile ilgili genellikle geri bildirimin de\u011ferine veya sadece belirlenmi\u015f \u00f6\u011frenme g\u00f6revlerini \u00f6\u011frenenin tamamlamas\u0131n\u0131n bir bile\u015feni olarak odaklan\u0131r\u0131z. Bu nedenle, bu b\u00f6l\u00fcm, geri bildirim mekanizmalar\u0131na odaklanarak de\u011ferlendirme uygulamalar\u0131n\u0131n \u00f6z\u00fcn\u00fcn d\u00f6n\u00fc\u015f\u00fcm\u00fcn\u00fc kolayla\u015ft\u0131rmak i\u00e7in \u00f6\u011frenen izleme verilerinden nas\u0131l yararlan\u0131labilece\u011fini ara\u015ft\u0131rmaktad\u0131r. Bu ama\u00e7la, \u00f6\u011frenme analiti\u011fi ve e\u011fitsel veri madencili\u011fi (\u00d6A \/ EVM) konusundaki ara\u015ft\u0131rmalar\u0131n geni\u015f kapsaml\u0131 bir \u00f6rne\u011fi ile \u00f6rneklenen veri ile geli\u015ftirilmi\u015f geri bildirimlerin yarat\u0131lmas\u0131 ve sunulmas\u0131na y\u00f6nelik mevcut yakla\u015f\u0131mlar\u0131 vurgulay\u0131p tart\u0131\u015f\u0131yoruz.<\/span><\/p>\n\n

Teorik Geribildirim Modelleri<\/h3>\n

E\u011fitim ba\u011flamlar\u0131nda birle\u015fik bir geri bildirim tan\u0131m\u0131 bulunmamakla birlikte, \u00f6\u011frenme \u00fczerindeki etkilerinin \u00e7e\u015fitli kapsaml\u0131 analizleri yap\u0131lm\u0131\u015ft\u0131r (\u00f6r. Evans, 2013; Hattie ve Timperley, 2007; Kluger ve DeNisi, 1996). \u00d6zetle, g\u00fc\u00e7l\u00fc g\u00f6rg\u00fcl\/deneysel kan\u0131tlar, geri bildirimin \u00f6\u011frenenin \u00f6\u011frenmesini etkileyen en g\u00fc\u00e7l\u00fc fakt\u00f6rlerden biri oldu\u011funu g\u00f6stermektedir (Hattie, 2008). \u00c7al\u0131\u015fmalar\u0131n \u00e7o\u011funlu\u011fu, geri bildirimin sa\u011flanmas\u0131n\u0131n akademik performans \u00fczerinde olumlu bir etkiye sahip oldu\u011fu sonucuna varm\u0131\u015ft\u0131r. Bununla birlikte, genel etki b\u00fcy\u00fckl\u00fc\u011f\u00fcn\u00fcn de\u011fi\u015fmesi ve baz\u0131 durumlarda olumsuz bir etkiye sahip oldu\u011fu kaydedilmi\u015ftir. \u00d6rne\u011fin, Kluger ve DeNisi (1996) taraf\u0131ndan yap\u0131lan bir \u00fcst analiz, yetersiz bir detay seviyesi veya verilen bilginin ilgisizli\u011fi ile karakterize edilen k\u00f6t\u00fc uygulanan geri bildirimlerin \u00f6\u011frenen performans\u0131 \u00fczerinde olumsuz bir etkisi olabilece\u011fini g\u00f6stermi\u015ftir. Bu durumda, yazarlar, \u00f6\u011frenenin geri bildirim oda\u011f\u0131 olan \u00fc\u00e7 d\u00fczey aras\u0131nda geri bildirime dikkat \u00e7ekmi\u015ftir: g\u00f6rev, g\u00fcd\u00fcleme ve \u00fcst g\u00f6rev seviyesi. \u00dc\u00e7\u00fc de e\u015fit derecede \u00f6nemlidir ve odakta kademeli olarak de\u011fi\u015febilir. Ek olarak, Shute (2008) geri bildirimi karma\u015f\u0131kl\u0131\u011f\u0131 ile ba\u011flant\u0131l\u0131 olarak s\u0131n\u0131fland\u0131rm\u0131\u015f ve olumsuz etki potansiyeli, hedef y\u00f6nelimi ile ba\u011flant\u0131, motivasyon, bili\u015fsel destek mekanizmalar\u0131ndaki varl\u0131\u011f\u0131, zamanlama veya farkl\u0131 \u00f6\u011frenen ba\u015far\u0131s\u0131 seviyeleri gibi geri bildirimin sa\u011flanmas\u0131n\u0131 etkileyen fakt\u00f6rleri analiz etmi\u015ftir. Shute, etkisini en \u00fcst d\u00fczeye \u00e7\u0131karmak i\u00e7in, bir \u00f6\u011frencinin eylemine cevap olarak verilen geri bildirimlerin, de\u011ferlendirme d\u0131\u015f\u0131, destekleyici, zaman\u0131nda ve \u00f6zel olmas\u0131 gerekti\u011fini belirtmi\u015ftir.<\/span><\/p>\n

\u00d6\u011frenmeyle geri bildirimi ili\u015fkilendiren erken modeller, b\u00fcy\u00fck \u00f6l\u00e7\u00fcde, \u00f6\u011frenciye sa\u011flanan bilgi t\u00fcrlerini tan\u0131mlamay\u0131 ama\u00e7lamaktad\u0131r. Temel olarak, bu \u00e7al\u0131\u015fmalar farkl\u0131 t\u00fcrdeki bilgilerin \u00f6\u011frencinin \u00f6\u011frenmesi \u00fczerine oynayabilece\u011fi etkiyi karakterize etmeye \u00e7al\u0131\u015fm\u0131\u015ft\u0131r (Kulhavy ve Stock, 1989). Geri bildirimin ilk kavramsalla\u015ft\u0131r\u0131lmas\u0131, \u00f6\u011frenmenin ger\u00e7ek ve istenen durumu aras\u0131ndaki a\u00e7\u0131\u011f\u0131n nas\u0131l kapanabilece\u011fine ili\u015fkin \u00f6\u011frenme biliminin kuramsalla\u015ft\u0131rmas\u0131ndaki farkl\u0131l\u0131klardan kaynaklanm\u0131\u015ft\u0131r (bk. Tarihsel inceleme, Kluger ve DeNisi, 1996; Mory, 2004). Mory (2004)\u2019e g\u00f6re, \u00e7a\u011fda\u015f modeller, \u00f6\u011frencilerin g\u00fc\u00e7l\u00fc bir beceri paketi kulland\u0131klar\u0131 g\u00f6revlerle me\u015fgul olma hallerinde oldu\u011fu gibi (Butler ve Winne, 1995) geri bildirimleri \u00f6z y\u00f6netimli \u00f6\u011frenme (\u00d6Y\u00d6) ba\u011flam\u0131nda g\u00f6ren eski paradigmalar \u00fczerine in\u015fa edilmi\u015ftir . Bu beceriler, hedeflerin belirlenmesi, stratejilerin d\u00fc\u015f\u00fcn\u00fclmesi, do\u011fru stratejilerin se\u00e7ilmesi ve bu stratejilerin hedeflere y\u00f6nelik ilerleme \u00fczerindeki etkilerinin izlenmesi, \u00f6\u011frencilerin ba\u015far\u0131s\u0131 ile ili\u015fkilidir (Butler ve Winne, 1995; Pintrich, 1999; Zimmerman, 1990). Geri bildirim ve \u00f6z y\u00f6netimli \u00f6\u011frenme aras\u0131ndaki teorik sentezlerinin bir par\u00e7as\u0131 olarak Butler ve Winne (1995, s. 248), modellerine iki geri besleme d\u00f6ng\u00fcs\u00fc yerle\u015ftirmi\u015ftir. \u0130lk d\u00f6ng\u00fc, bili\u015fsel sistem i\u00e7inde yer al\u0131r ve bireylerin kendi i\u00e7 bilgilerini ve inan\u00e7lar\u0131n\u0131, ama\u00e7lar\u0131n\u0131, taktiklerini ve stratejilerini izleme ve \u00f6\u011frenme senaryosunun gerektirdi\u011fi \u015fekilde de\u011fi\u015ftirmelerini sa\u011flar. \u0130kinci d\u00f6ng\u00fc, bir g\u00f6revle ilgilenen bir \u00f6\u011frenciden kaynaklanan \u00fcr\u00fcn \u00f6l\u00e7\u00fcl\u00fcrken ortaya \u00e7\u0131kar ve \u00f6\u011frenciye geri iletilen d\u0131\u015f geri bildirimin yarat\u0131lmas\u0131n\u0131 sa\u011flar; \u00f6rne\u011fin, bir de\u011ferlendirme puan\u0131 veya bir g\u00f6revin tamamlanmas\u0131 \u00fczerine yorum yapan bir \u00f6\u011freten.<\/span><\/p>\n

Hattie ve Timperley (2007) geri bildirim ve bunun ba\u015far\u0131ya olan etkisi \u00fczerine en etkili \u00e7al\u0131\u015fmalardan birini sa\u011flam\u0131\u015ft\u0131r. Yazarlar\u0131n kavramsal analizleri, bir \u00f6\u011frencinin performans\u0131 veya anlay\u0131\u015f\u0131 hakk\u0131nda bir arac\u0131 taraf\u0131ndan sa\u011flanan bilgiler olarak geri bildirim tan\u0131mlar\u0131 ile desteklenmi\u015ftir<\/i>. Yazarlar, kavram etraf\u0131nda dile getirilen herhangi bir geri bildirimin, \u00f6\u011frencinin mevcut anlay\u0131\u015f\u0131 ile istenen \u00f6\u011frenme hedefi aras\u0131ndaki uyu\u015fmazl\u0131\u011f\u0131 azaltmay\u0131 ama\u00e7lamas\u0131 gerekti\u011fi \u015feklinde bir geribildirim modeli \u00f6nermi\u015ftir. Bu nedenle, geribildirim \u00fc\u00e7 soru etraf\u0131nda \u00e7er\u00e7evelenebilir: nereye gidiyorum, nas\u0131l gidiyorum ve bundan sonra nereye olaca\u011f\u0131m? <\/i><\/span>Hattie ve Timperley (2007), bu sorular\u0131n her birinin d\u00f6rt farkl\u0131 seviyeye uygulanmas\u0131 gerekti\u011fini \u00f6nerdi: \u00f6\u011frenme g\u00f6revi, \u00f6\u011frenme s\u00fcreci, \u00f6z d\u00fczenleme ve ki\u015fi.<\/i><\/span> \u00d6\u011frenme g\u00f6revi seviyesi basit bir g\u00f6revin unsurlar\u0131n\u0131 ifade eder; \u00f6rne\u011fin, bir cevab\u0131n do\u011fru veya yanl\u0131\u015f olup olmad\u0131\u011f\u0131n\u0131 \u00f6\u011frenene bildirmek. \u00d6\u011frenme s\u00fcreci, farkl\u0131 zamanlarda \u00e7e\u015fitli g\u00f6revler i\u00e7eren genel \u00f6\u011frenme hedeflerini ifade eder. \u00d6z y\u00f6netim seviyesi, \u00f6\u011frenme hedefleri \u00fczerine derin d\u00fc\u015f\u00fcnme, do\u011fru stratejiyi se\u00e7me ve bu hedeflere do\u011fru ilerlemeyi izleme kapasitesini ifade eder. Son olarak, benlik d\u00fczeyi, \u00f6\u011frenme deneyimi ile ili\u015fkili olmayabilecek soyut ki\u015filik \u00f6zelliklerini ifade eder. S\u00fcre\u00e7 ve d\u00fczenleme seviyelerinin, derin \u00f6\u011frenmeyi ve g\u00f6rev ustal\u0131\u011f\u0131n\u0131 artt\u0131rmada en etkili oldu\u011fu iddia edilmektedir. G\u00f6rev seviyesinde geri bildirim, sadece \u00f6nceki iki seviyeye ek olarak etkilidir; \u00f6z d\u00fczeydeki geri bildirimin en az etkili oldu\u011fu g\u00f6sterilmi\u015ftir. Bu \u00fc\u00e7 soru ve d\u00f6rt geri bildirim seviyesi, geri bildirimi zamanlama, pozitif ve negatif iletiler (kutupluluk da denir) gibi di\u011fer y\u00f6nlerle ve ayn\u0131 zamanda bir de\u011ferlendirme arac\u0131n\u0131n bir par\u00e7as\u0131 olarak geri bildirimi d\u00e2hil etmenin sonu\u00e7lar\u0131 ile ba\u011flant\u0131 kurma hakk\u0131 sa\u011flar. Bu y\u00f6nlerin pozitif veya negatif olabilen birbirine ba\u011f\u0131ml\u0131 bir etkiye sahip oldu\u011fu g\u00f6sterilmi\u015ftir (Nicol ve Macfarlane-Dick, 2006).<\/span><\/p>\n

Yerle\u015fik geri bildirim modellerini incelerken, Boud ve Molloy (2013), genellikle kaynak k\u0131s\u0131tlamalar\u0131, \u00f6nerilen geri bildirim modelleri veya en az\u0131ndan her \u00f6\u011frencinin i\u00e7in de\u011ferlendirici, destekleyici, zaman\u0131nda ve \u00f6zel geri bildirim \u00fcretme mekanizmas\u0131n\u0131n elveri\u015fli olmayaca\u011f\u0131 veya en az\u0131ndan \u00e7a\u011fda\u015f e\u011fitim senaryolar\u0131 i\u00e7erisinde s\u00fcrd\u00fcr\u00fclebilir olmamas\u0131 nedeniyle zaman zaman \u00f6\u011frenciler ve e\u011fitim ortam\u0131 ile ilgili ger\u00e7ek\u00e7i olmayan varsay\u0131mlara dayand\u0131klar\u0131n\u0131 savunmu\u015flard\u0131r. Bu noktada, \u00d6A \/ EVM \u00e7al\u0131\u015fmas\u0131 geri bildirimlerin d\u00fczensiz ve tek y\u00f6nl\u00fc bir durumdan etkin birimler aras\u0131nda aktif bir diyaloga ta\u015f\u0131nmas\u0131nda \u00f6nemli bir rol oynayabilir.<\/span><\/p>\n\n

VER\u0130 DESTEKL\u0130 GER\u0130 B\u0130LD\u0130R\u0130M<\/h2>\n

\u00d6\u011frenmenin \u00f6zelliklerini geli\u015ftirmek i\u00e7in \u00e7ok miktarda veri kullanan ilk giri\u015fimler, uyarlanabilir hiper ortam<\/i><\/span> (Brusilovsky, 1996; Kobsa, 2007), ak\u0131ll\u0131 \u00f6\u011fretici sistemleri<\/i><\/span> (A\u00d6S'ler) (Corbett, Koedinger ve Anderson, 1997; Graesser, Conley ve Olney) ve akademik analitik (Baepler ve Murdoch, 2010; Campbell, DeBlois ve Oblinger, 2007; Goldstein ve Katz, 2005) gibi alanlara kadar dayand\u0131r\u0131labilir. Bu ara\u015ft\u0131rman\u0131n \u00e7o\u011fu, e\u011fitim uygulamalar\u0131n\u0131 ilerletmek amac\u0131yla, e\u011fitim ortam\u0131n\u0131n ara\u015ft\u0131r\u0131lmas\u0131na y\u00f6nelik veri yo\u011fun yakla\u015f\u0131mlara ortak ilgi duyan \u00d6A \/ EVM ara\u015ft\u0131rma topluluklar\u0131 i\u00e7erisinde ger\u00e7ekle\u015ftirilmi\u015ftir (Baker ve Inventado, 2014). Bu topluluklar\u0131n bir\u00e7ok benzerli\u011fi olsa da \u00d6A ve EVM aras\u0131nda baz\u0131 kabul edilmi\u015f farkl\u0131l\u0131klar vard\u0131r (Baker ve Siemens, 2014). \u00d6rne\u011fin, EVM, \u00d6A\u2019lar\u0131n b\u00fct\u00fcnsel sistemler i\u00e7inde yer alan insan liderli\u011findeki ara\u015ft\u0131rmalar\u0131n aksine, otomatik ke\u015fif y\u00f6ntemleri \u00fczerine daha indirgemeci bir odaklanmaya sahiptir. Baker ve Inventado (2014), \u00d6A ve EVM aras\u0131ndaki temel farkl\u0131l\u0131klar\u0131n, \u00e7o\u011funlukla tercih edilen metodolojilerde olmad\u0131\u011f\u0131n\u0131 ancak odakta, ara\u015ft\u0131rma sorular\u0131nda ve modellerin nihai kullan\u0131m\u0131nda oldu\u011funu belirtmi\u015ftir.<\/span><\/p>\n

\u00d6A \/ EVM'yi geri bildirim merce\u011fi arac\u0131l\u0131\u011f\u0131yla de\u011ferlendirirken, ara\u015ft\u0131rma yakla\u015f\u0131mlar\u0131 geri bildirimin y\u00f6n\u00fc ve al\u0131c\u0131s\u0131 ile ilgili olarak farkl\u0131l\u0131klar g\u00f6sterir. \u00d6rne\u011fin, \u00d6A giri\u015fimleri genel olarak \u00f6\u011freneni \u00f6\u011frenme s\u00fcrecinde geli\u015ftirmeye y\u00f6nelik geri bildirim sa\u011flar (\u00f6r. \u00f6z y\u00f6netim, hedef belirleme, motivasyon, stratejiler ve taktikler). Buna kar\u015f\u0131l\u0131k, EVM giri\u015fimleri, \u00f6\u011frenme ortam\u0131ndaki de\u011fi\u015fiklikleri ele almak i\u00e7in geri bildirim sa\u011flama konusuna odaklanma e\u011filimindedir (\u00f6r. bir g\u00f6revi de\u011fi\u015ftirecek ipu\u00e7lar\u0131 sa\u011flama, \u00e7evreyi ilgili kaynaklarla donatacak bulu\u015fsal y\u00f6ntemler vb.). Bu genellemelerin topluluklar\u0131n zor bir s\u0131n\u0131fland\u0131rmas\u0131 olmad\u0131\u011f\u0131n\u0131, daha ziyade \u00d6A \/ EVM \u00e7al\u0131\u015fmalar\u0131nda disiplin ge\u00e7mi\u015flerini ve ilgi alanlar\u0131n\u0131 yans\u0131tan g\u00f6zlemlenen bir e\u011filim oldu\u011funu not etmek \u00f6nemlidir. A\u015fa\u011f\u0131daki b\u00f6l\u00fcm, \u00f6\u011frenenlerin \u00f6\u011frenmelerine yard\u0131mc\u0131 olmak i\u00e7in geri bildirim sa\u011flama ile ilgili hem EVM hem de \u00d6A topluluklar\u0131ndaki \u00e7al\u0131\u015fmalar\u0131 daha da a\u00e7maktad\u0131r.<\/span><\/p>\n\n

    \n \t
  1. \n
      \n \t
    1. \n
        \n \t
      1. \n
          \n \t
        1. \n

          E\u011fitsel Veri Madencili\u011finde Geribildirime Yakla\u015f\u0131mlar<\/h4>\n<\/li>\n<\/ol>\n<\/li>\n<\/ol>\n<\/li>\n<\/ol>\n<\/li>\n<\/ol>\n

          EVM'de yap\u0131lan ara\u015ft\u0131rmalar, e\u011fitimde yapay zek\u00e2 (EYZ) ve ak\u0131ll\u0131 \u00f6\u011fretici sistemleri (A\u00d6S'ler) gibi disiplinlerle ba\u011flant\u0131l\u0131d\u0131r ve ili\u015fkilidir (Pinkwart, 2016). Geri bildirim s\u00fcre\u00e7leriyle ilgili olarak, \u00e7ok say\u0131da EVM ara\u015ft\u0131rma giri\u015fimi, uyarlanm\u0131\u015f ve ki\u015fiselle\u015ftirilmi\u015f geri bildirim veya \u00f6nerilerin \u00f6\u011frenenlere etkisini geli\u015ftirmek ve de\u011ferlendirmekle ilgilenmektedir (Hegazi ve Abugroon, 2016). Bu \u00e7al\u0131\u015fma, \u00f6\u011frenen modellemesi ve \/ veya tahmine dayal\u0131 modelleme ara\u015ft\u0131rmas\u0131na dayanmaktad\u0131r. Temel olarak, odak noktas\u0131, \u00f6\u011frencinin \u00f6zel ihtiya\u00e7lar\u0131na cevap vermek i\u00e7in geri bildirimin verilmesini sa\u011flayan \u00f6zel sistemler olu\u015fturmak, b\u00f6ylece \u00f6\u011frenmedeki geli\u015fmeleri kolayla\u015ft\u0131rmak, akademik performans\u0131 g\u00fc\u00e7lendirmek (olumlu) veya \u00f6\u011frencilerin belirli davran\u0131\u015flar\u0131 yerine getirmelerini engellemek olmu\u015ftur (Romero; Ventura, 2013).<\/span><\/p>\n

          Geri bildirim sa\u011flama ile ilgilenen EVM yakla\u015f\u0131mlar\u0131, genel olarak baz\u0131 istisnalar d\u0131\u015f\u0131nda, g\u00f6rev d\u00fczeyinde geri bildirime vurgu yapm\u0131\u015ft\u0131r (\u00f6r. Arroyo, Meheranian ve Woolf, 2010; Kinnebrew ve Biswas, 2012; Lewkow, Zimmerman, Riedesel ve Essa, 2015; Madhyastha ve Tanimoto, 2009). EVM \u00fczerine yap\u0131lan erken ara\u015ft\u0131rmalar (bk. 2008 ve 2009'daki EVM konferans\u0131 bildirileri), veri odakl\u0131 modelleme (\u00f6r. Mavrikis, 2008), \u00f6\u011fretim g\u00f6revlileri (\u00f6r. Jeong) taraf\u0131ndan (\u00f6r. Jeong ve Biswas, 2008), talep \u00fczerine ve anl\u0131k bilgi istemlerinin sa\u011flanmas\u0131 (Lynch, Ashley, Aleven ve Pinkwart, 2008) de\u011ferlendirme g\u00f6revlerinin bir par\u00e7as\u0131 olarak ayr\u0131nt\u0131l\u0131 geri bildirim (Pechenizkiy, Calders, Vasilyeva ve De Bra, 2008), gecikmi\u015f geri bildirimi (Feng, Beck ve Heffernan, 2009) ve s\u00fcre\u00e7 modellemesi (Pechenizkiy, Trcka, Vasilyeva, van der Aalst ve De Bra, 2009) yoluyla \u00f6\u011frenenlere geri bildirim sa\u011flamay\u0131 ama\u00e7layan \u00e7ok \u00e7e\u015fitli yakla\u015f\u0131mlar ortaya koymu\u015ftur. Bu EVM \u00e7al\u0131\u015fmas\u0131, gelecekteki sistemleri bilgilendirmek i\u00e7in geri bildirim mekanizmalar\u0131n\u0131n ara\u00e7salla\u015ft\u0131r\u0131lmas\u0131 ve bu modellerin nas\u0131l geli\u015ftirilebilece\u011finin anla\u015f\u0131lmas\u0131 i\u00e7in ileriye d\u00f6n\u00fck \u00e7abalar\u0131 i\u00e7ermektedir. Ba\u015fka bir deyi\u015fle, algoritmalar potansiyel olarak daha iyi geri bildirim sa\u011flayan yeni sistemlerin tasar\u0131m\u0131n\u0131 etkileyecek teknik bilgi sa\u011flayabilir. \u00d6rne\u011fin, Barker-Plummer, Cox ve Dale (2009), daha iyi algoritmalar\u0131n sa\u011flanmas\u0131n\u0131n \u00f6tesine ge\u00e7me ve g\u00f6rev d\u00fczeyinde geri bildirimin epistemik ve pedagojik durumdan nas\u0131l etkilendi\u011fini anlama gere\u011fini \u00f6ne s\u00fcrd\u00fcler. Ba\u015fka bir deyi\u015fle, \u00f6\u011frenme s\u00fcrecindeki geri bildirim veya \u00f6z y\u00f6netim becerileri hakk\u0131ndaki bilgiler, g\u00f6rev d\u00fczeyinde geri bildirimin \u00e7er\u00e7eveye al\u0131nmas\u0131na yard\u0131mc\u0131 olabilir.<\/span><\/p>\n

          Uyarlanabilir geri bildirim ile ilgili \u00e7al\u0131\u015fmalar\u0131n b\u00fcy\u00fck bir k\u0131sm\u0131 ak\u0131ll\u0131 \u00f6\u011fretici sistemleri (A\u00d6S'ler; \u00f6rne\u011fin, Abbas ve Sawamura, 2009; Eagle ve Barnes, 2013; Feng vd., 2009), \u00f6\u011frenme y\u00f6netim sistemleri (\u00d6YS; Dominguez, Yacef ve Curran, 2010; Lynch vd., 2008; Pechenizkiy vd., 2008) veya belirli bilgi alanlar\u0131ndaki \u00f6\u011frencilere bir dizi \u00f6\u011frenme g\u00f6revi sa\u011flayan e\u015fde\u011fer tek kullan\u0131c\u0131l\u0131 sistemler arac\u0131l\u0131\u011f\u0131 ile geli\u015ftirilmi\u015ftir. Bu sistemlerin \u00e7o\u011fu, \u00f6\u011frenen modellerini farkl\u0131 \u015fekillerde \u00e7eker: \u00f6rne\u011fin \u00f6\u011frenen davran\u0131\u015f\u0131n\u0131n izleri, bilgi, ba\u015far\u0131, bili\u015fsel durumlar veya duygusal durumlar. Bu modellere dayanarak, sistem genellikle sonraki ad\u0131m ipu\u00e7lar\u0131 gibi \u00e7e\u015fitli g\u00f6rev d\u00fczeyinde geri bildirim t\u00fcrleri sunar (\u00f6r. Peddycord, Hicks ve Barnes, 2014); bayrak geri bildirimi olarak da bilinen do\u011fruluk ipu\u00e7lar\u0131 (Barker \u2013 Plummer, Cox ve Dale, 2011); olumlu ya da cesaretlendirici ipu\u00e7lar\u0131 (Stefanescu, Rus ve Graesser, 2014); sonraki ad\u0131mlar veya g\u00f6revlerle ilgili \u00f6neriler (Ben-Naim, Bain ve Marcus, 2009); veya yukar\u0131dakilerin \u00e7e\u015fitli kombinasyonlar\u0131. Bu nedenle, davran\u0131\u015f modellemesi \u00fczerine yap\u0131lan \u00e7al\u0131\u015fmalar, EVM ara\u015ft\u0131rmalar\u0131nda otomatik geri bildirim s\u00fcre\u00e7leri geli\u015ftirmenin ayr\u0131lmaz bir par\u00e7as\u0131 olmu\u015ftur (DeFalco, Baker ve D\u2019Mello, 2014).<\/span><\/p>\n

          Son y\u0131llarda, EVM'nin \u00f6\u011frenen modellemesindeki \u00e7al\u0131\u015fmas\u0131, ara\u015ft\u0131rmac\u0131lar\u0131n daha az yap\u0131land\u0131r\u0131lm\u0131\u015f \u00f6\u011frenme g\u00f6revleri i\u00e7in geri bildirim mekanizmalar\u0131 \u00fcretmelerine izin veren yeni y\u00f6ntemlerin ortaya \u00e7\u0131kmas\u0131yla zenginle\u015ftirilmi\u015ftir. Bir \u00f6rnek \u00f6\u011frenci yazma \u00e7al\u0131\u015fmas\u0131 bi\u00e7imlendirici ve \u00f6zetleyici geri bildirim sa\u011flamay\u0131 i\u00e7erir (Allen ve McNamara, 2015; Crossley, Kyle, McNamara ve Allen, 2014). Daha karma\u015f\u0131k alg\u0131lay\u0131c\u0131 cihazlar\u0131n ve tahmine dayal\u0131 algoritmalar\u0131n ortaya \u00e7\u0131kmas\u0131, g\u00fcven, tutum, ki\u015filik, motivasyon (Ezen-Can ve Boyer, 2015) ve etkileme gibi daha karma\u015f\u0131k be\u015feri boyutlar\u0131n\u0131n izlerini d\u00e2hil ederek \u00f6\u011frenen modellerinin geli\u015ftirilmesine olanak sa\u011flam\u0131\u015ft\u0131r (Fancsali, 2014). Bu daha farkl\u0131 veri yard\u0131mlar\u0131 her \u00f6\u011frenen i\u00e7in ki\u015fiselle\u015ftirilebilecek daha iyi cevap veren uyarlanabilir geri bildirim mekanizmalar\u0131n\u0131n geli\u015ftirilmesine yard\u0131mc\u0131 olur. \u00d6\u011frenci modellerinin karma\u015f\u0131kl\u0131\u011f\u0131na paralel olarak, baz\u0131 ara\u015ft\u0131rmac\u0131lar a\u00e7\u0131k \u00f6\u011frenen modelleme (A\u00d6M) kavram\u0131n\u0131 ara\u015ft\u0131rd\u0131lar (OLM; Bull ve Kay, 2016). A\u00d6M d\u00fc\u015f\u00fcncesi g\u00f6rsel veri sunumuna benzer ancak bir ara\u00e7 taraf\u0131ndan olu\u015fturulan modele uygulan\u0131r. A\u00d6M'ler EYZ toplulu\u011funda, tavsiyeler, d\u00fczeltici eylemler veya bir sonraki ad\u0131mla ilgili ipu\u00e7lar\u0131yla kar\u015f\u0131la\u015ft\u0131r\u0131ld\u0131\u011f\u0131nda daha az kuralc\u0131 geri bildirim bi\u00e7imleri sa\u011flama pe\u015finde ko\u015fmu\u015ftur. A\u00d6M'ler, kullan\u0131c\u0131n\u0131n (\u00f6\u011frenen, \u00f6\u011fretmen, akranlar, vb.) insan taraf\u0131ndan anla\u015f\u0131labilir formlarda sunulan \u00f6\u011frenen modelinin i\u00e7eri\u011fini g\u00f6r\u00fcnt\u00fclemesine ve yans\u0131tmas\u0131na (hatta incelemesine) izin verdi\u011fi i\u00e7in, yenilenmi\u015f ilgi g\u00f6rm\u00fc\u015ft\u00fcr. Bu modellerin avantajlar\u0131ndan biri, \u00f6\u011frenenlerin \u00f6z y\u00f6netim becerilerini yans\u0131tmas\u0131na ve te\u015fvik etmesine yard\u0131mc\u0131 olmakt\u0131r.<\/span><\/p>\n

          Son zamanlarda, kitlesel a\u00e7\u0131k \u00e7evrimi\u00e7i derslerin artan pop\u00fclaritesi nedeniyle, bilimsel EVM \u00e7al\u0131\u015fmalar\u0131nda geri bildirimlerin art\u0131r\u0131lmas\u0131 g\u00fc\u00e7 kazand\u0131 (KA\u00c7D'ler; Wen, Yang ve Rose, 2014). KA\u00c7D'lerde (Pardos, Bergner, Seaton ve Pritchard, 2013) \u00f6\u011frenen \u00e7al\u0131\u015fmalar\u0131 i\u00e7in ki\u015fiselle\u015ftirilmi\u015f geri bildirim sa\u011flaman\u0131n yan\u0131 s\u0131ra, b\u00fcy\u00fck topluluklarda y\u00fcksek kalitede geri bildirime uygun eri\u015fim sa\u011flamak i\u00e7in mekanizma \u00fcretmeye de ilgi duyulmaktad\u0131r. Baz\u0131 geri bildirim \u00e7\u00f6z\u00fcmleri, karma\u015f\u0131k, a\u00e7\u0131k u\u00e7lu \u00f6\u011frenme g\u00f6revlerini video tabanl\u0131 geri bildirimler arac\u0131l\u0131\u011f\u0131yla (Ostrow ve Heffernan, 2014) veya akran geri bildirimleri \u00fczerine temellendirerek (Piech vd., 2013) ele almaktad\u0131r.<\/span><\/p>\n

          EVM'de \u00f6\u011frencilere g\u00f6rev d\u00fczeyinde, ger\u00e7ek zamanl\u0131 geri bildirim sa\u011flama konusunda b\u00fcy\u00fck bir vurgu olmas\u0131na ra\u011fmen, di\u011fer yakla\u015f\u0131mlar da ara\u015ft\u0131r\u0131lm\u0131\u015ft\u0131r. \u00d6rne\u011fin, baz\u0131 \u00e7abalar \u00f6\u011frencilerin \u00f6\u011frenme s\u00fcrecindeki aksakl\u0131klar\u0131 \u00f6nlemek i\u00e7in gecikmeli geri bildirim sa\u011flamaya odaklanm\u0131\u015ft\u0131r (Feng vd., 2009; Johnson ve Zaiane, 2012). EVM'nin \u201cd\u00fczeltici\u201d geri bildirimin \u00f6tesine ge\u00e7mesi ve kutuplulu\u011fun (olumlu, olumsuz veya birle\u015fik geri bildirim) ve geri besleme zamanlamas\u0131n\u0131n \u00f6\u011frencilerin diyalo\u011funda (Ezen-Can ve Boyer, 2013), g\u00fcvende (Lang, Heffernan, Ostrow ve Wang, 2015) veya i\u015fbirlikli senaryolarda (Olsen, Aleven ve Rummel, 2015) oynayabilece\u011fi rol\u00fc anlamak da ilgi \u00e7ekmi\u015ftir. Sistematik olarak farkl\u0131 seviyelerde \u00f6\u011frenen faaliyetini hedefleyen geri bildirim sa\u011flama, baz\u0131 \u00f6rnekler sunulmu\u015f olsa da hen\u00fcz hak etti\u011fi ilgiyi g\u00f6rmemi\u015ftir. \u00d6rne\u011fin, Arroyo vd. (2010) 'da dijital \u00f6\u011frenme yolda\u015f\u0131 bili\u015fsel (ipu\u00e7lar\u0131), duygusal (\u00f6vg\u00fc) ve \u00fcst bili\u015fsel seviyelerde (\u00f6r. ilerleme g\u00f6steren) geri bildirim veren akranlar olarak hareket etmi\u015ftir. G\u00f6rev d\u00fczeyinde bili\u015fsel seviye veya ipucu sa\u011flanmas\u0131 \u00f6nerildi. \u0130lerleme g\u00f6sterme, \u00f6z derin d\u00fc\u015f\u00fcnme1<\/a><\/sup> kapasitesine de\u011findi (yani bir hedefe y\u00f6nelik ilerlemeyi izlemek). \u00d6z y\u00f6netimli \u00f6\u011frenmeye y\u00f6nelik di\u011fer geri bildirim \u00f6rnekleri, \u00d6Y\u00d6 davran\u0131\u015f\u0131n\u0131 ve \u00f6z de\u011ferlendirmeyi desteklemeye (Bouchet, Azevedo, Kinnebrew ve Biswas, 2012); \u00fcst d\u00fczey \u00f6\u011frenci stratejilerini bili\u015fsel desteklemeye (Eagle ve Barnes, 2014); bilgi in\u015fas\u0131 stratejilerinin \u00f6nerilmesine (Kinnebrew ve Biswas, 2012) ve geri bildirimin \u00f6\u011frencilerin \u00f6\u011frenme s\u00fcre\u00e7lerinde nas\u0131l yer ald\u0131\u011f\u0131n\u0131 anlamaya (Howard, Johnson ve Neitzel, 2010) odaklanm\u0131\u015ft\u0131r.<\/span><\/p>\n\n

            \n \t
          1. \n
              \n \t
            1. \n
                \n \t
              1. \n
                  \n \t
                1. \n

                  \u00d6\u011frenme Analiti\u011finde Geribildirime Yakla\u015f\u0131mlar<\/h4>\n<\/li>\n<\/ol>\n<\/li>\n<\/ol>\n<\/li>\n<\/ol>\n<\/li>\n<\/ol>\n

                  Los Angeles'taki ara\u015ft\u0131rmada geri bildirime odaklanma genellikle \u00f6\u011frencinin \u00f6\u011frenme durumunu \u00e7e\u015fitli payda\u015flara, yani \u00f6\u011fretmenlere, \u00f6\u011frencilere veya y\u00f6neticilere iletme ihtiyac\u0131 olarak yorumlan\u0131r. \u0130lk \u00d6A ara\u015ft\u0131rmalar\u0131 (\u00f6r. LAK 2011 ve 2012 konferans\u0131 i\u015flemleri) kendi ba\u015f\u0131na geri bildirime odaklanmamas\u0131na kar\u015f\u0131n, \u00d6A'y\u0131 \u201charekete ge\u00e7irilebilir zek\u00e2\u201d \u00fcretmek i\u00e7in (McKay, Miller ve Tritz, 2012) \u00f6l\u00e7eklenebilir geri bildirim s\u00fcre\u00e7leriyle d\u00f6ng\u00fcy\u00fc kapatmas\u0131 gereken bir disiplin olarak vurgulam\u0131\u015ft\u0131r (Clow, 2012; Lonn, Aguilar ve Teasley, 2013). \u00d6A ara\u015ft\u0131rmalar\u0131, geri bildirimin, insanlara \u00f6\u011frenmenin eylemlilik ve do\u011fas\u0131na dair farkl\u0131 anlay\u0131\u015flar\u0131yla \u00e7ok say\u0131da disipline ait sesler arac\u0131l\u0131\u011f\u0131yla iletildi\u011fini kabul etmi\u015ftir (Suthers ve Verbert, 2013). Buna paralel olarak, Wise (2014) veri odakl\u0131 \u00f6\u011frenme m\u00fcdahalelerinin tasar\u0131m\u0131n\u0131, kendi sosyok\u00fclt\u00fcrel ba\u011flamlar\u0131nda nas\u0131l konumland\u0131klar\u0131n\u0131n fark\u0131ndal\u0131\u011f\u0131 ve \u00f6\u011frenen deste\u011fini ele alma amac\u0131 ile y\u00fcklemi\u015ftir. Ba\u011flam\u0131n \u00f6nemi nedeniyle, veri destekli geri bildirimin alg\u0131lanmas\u0131 ve yorumlanmas\u0131, \u00d6A geri bildirimi ile ilgili ara\u015ft\u0131rmalarda ayr\u0131 bir tema olmu\u015ftur. \u00d6A toplulu\u011fu, analitik ve payda\u015flar aras\u0131ndaki diyalogun ara\u015ft\u0131rmac\u0131lar taraf\u0131ndan \u00f6ng\u00f6r\u00fcld\u00fc\u011f\u00fc gibi ger\u00e7ekle\u015fmesini sa\u011flamak i\u00e7in kan\u0131t ve uygulamalar\u0131 ara\u015ft\u0131rm\u0131\u015ft\u0131r. \u00d6rne\u011fin, Corrin ve de Barba (2015) panolardaki \u00f6\u011frencilerin alg\u0131lar\u0131n\u0131 ara\u015ft\u0131rm\u0131\u015ft\u0131r; Beheshitha, Hatala, Ga\u0161evi\u0107 ve Joksimovi\u0107 (2016), farkl\u0131 ba\u015far\u0131 hedef y\u00f6nelimli \u00f6\u011frencilerin g\u00f6sterge panosu geri bildirimlerini ayn\u0131 \u015fekilde alg\u0131lay\u0131p alg\u0131lamad\u0131klar\u0131n\u0131 incelemi\u015ftir ve birka\u00e7 \u00e7al\u0131\u015fma, nitel g\u00f6r\u00fc\u015fmeleri veya insan yorumlay\u0131c\u0131lar\u0131n \u00e7al\u0131\u015fmalar\u0131n\u0131 veri odakl\u0131 analizlerle birle\u015ftirerek daha verimli bir ara\u015ft\u0131rma yapman\u0131n yollar\u0131n\u0131 konu edinmi\u015ftir (Arnold, Lonn ve Pistilli, 2014; Clow, 2014; Mendiburo, Sulcer ve Hasselbring, 2014; Pardo, Ellis ve Calvo, 2015). \u00d6\u011frencilerin bir t\u00fcr \u00f6zete veya etkinliklerinin g\u00f6stergelerine maruz b\u0131rak\u0131lmas\u0131, Hattie ve Timperley (2007) taraf\u0131ndan \u00f6nerilen taksonomide somut bir geri bildirim d\u00fczeyi ile ili\u015fkilendirilemez. Bununla birlikte, g\u00f6sterge panelleri genellikle g\u00f6rev d\u00fczeyinde bilgiler i\u00e7erir, \u00e7\u00fcnk\u00fc \u00f6\u011frenme s\u00fcreci veya \u00f6z y\u00f6netim becerileri hakk\u0131nda bilgi edinmek \u00e7ok daha zordur.<\/span><\/p>\n

                  EVM'ye benzer \u015fekilde, \u00d6A toplulu\u011funun ilgisi, Hattie ve Timperley (2007) taraf\u0131ndan \u00f6nerilen taksonomideki \u00fc\u00e7\u00fcnc\u00fc seviye olan \u00f6z-izleme ve \u00f6z y\u00f6netim s\u00fcre\u00e7leri i\u00e7in \u00f6\u011frenenlere otomatik, \u00f6l\u00e7eklendirilmi\u015f ve ger\u00e7ek zamanl\u0131 geri bildirim sa\u011flamakt\u0131r. Bu y\u00f6nlendirme, g\u00f6rselle\u015ftirme, yans\u0131tma ve fark\u0131ndal\u0131k i\u00e7in ara\u00e7lar olarak \u00d6A uygulamalar\u0131n\u0131n istikrarl\u0131 bir \u015fekilde b\u00fcy\u00fcmesiyle elde edilmi\u015ftir (\u00f6r. Verbert, Duval, Klerkx, Govaerts ve Santos, 2013; Verbert vd., 2014). \u00d6zel g\u00f6rev d\u00fczeyinde geri bildirimler, EVM \/ A\u00d6S yakla\u015f\u0131mlar\u0131ndan daha az \u00f6n planda olsa da \u00d6A geri bildirimi yorumlama ve harekete kat\u0131lan insan-eylemlili\u011finin daha \u00e7ok \u00fczerinde durur. \u00d6A, \u00f6\u011frenme etkinliklerinin izlerini g\u00f6rselle\u015ftirerek s\u00fcre\u00e7 d\u00fczeyinde geri bildirimleri te\u015fvik etme e\u011filimindedir. \u00d6rne\u011fin, \u00f6\u011frenme g\u00f6sterge panelleri, \u00f6\u011frenenlerin hedefleri tan\u0131mlamas\u0131n\u0131 ve bu hedeflere do\u011fru ilerlemeyi izlemesini sa\u011flamak i\u00e7in harcanan zaman, kullan\u0131lan kaynaklar veya sosyal etkile\u015fim gibi veri kaynaklar\u0131n\u0131 yakalar (bk. Verbert vd., 2014). \u00d6\u011frenme g\u00f6sterge panolar\u0131n\u0131n son uygulamalar\u0131 zaman say\u0131s\u0131ndan veya \u00f6\u011frenme ile ilgili nesnelerin kullan\u0131lmas\u0131ndan kavramsalla\u015ft\u0131r\u0131lm\u0131\u015f bir s\u00fcre\u00e7le ilgili ilerlemeyi g\u00f6rselle\u015ftirmeye, \u00f6rne\u011fin sorgulamaya dayal\u0131 \u00f6\u011frenmeye y\u00f6nelik masa \u00fcst\u00fc g\u00f6rselle\u015ftirmelere (Charleer, Klerkx ve Duval, 2015), ya da yeterlilik grafikleri i\u00e7indeki \u00f6\u011frenme yollar\u0131n\u0131n g\u00f6rselle\u015ftirmelerine kayd\u0131rmaktad\u0131r(Kickmeier-Rust, Steiner ve Dietrich, 2015). Sosyal \u00f6\u011frenme analiti\u011finin bir par\u00e7as\u0131 olarak sosyal a\u011f analizi (Dawson, 2010; Dawson, Bakharia ve Heathcote, 2010) taraf\u0131ndan yap\u0131lan g\u00f6rselle\u015ftirmeler (\u00f6r. Ferguson ve Buckingham Shum, 2012), sosyal etkile\u015fim s\u00fcreci hakk\u0131nda pop\u00fcler bir geri bildirim t\u00fcr\u00fcd\u00fcr. Bunlar yak\u0131n zamanda \u00f6\u011frenenlerin, kiminle konu\u015ftuklar\u0131 \u00fczerine derin d\u00fc\u015f\u00fcnmelerini veya \u201cvah\u015fi do\u011fada\u201dki \u00f6\u011frenen a\u011flar\u0131nda, yani Twitter ya da Facebook gibi da\u011f\u0131t\u0131lm\u0131\u015f sosyal medyada ve \u00d6YS lerin \u00f6tesinde nerede konumland\u0131klar\u0131 konular\u0131na da geni\u015fletilmi\u015ftir (\u00f6r. Kitto, Pardo, Gasevi\u00e7 ve Dawson, 2016). Bu t\u00fcr a\u011f g\u00f6rselle\u015ftirmeleri, gruplara kolektif bilgi in\u015fas\u0131n\u0131n temsili olarak da sunulmu\u015ftur.<\/span><\/p>\n

                  \u00d6\u011frencinin \u00f6z y\u00f6netimli \u00f6\u011frenme yeterlili\u011fini geli\u015ftirmeye y\u00f6nelik geri bildirim, ba\u015flang\u0131\u00e7 a\u015famas\u0131ndad\u0131r. Bi\u00e7imlendirici geri bildirime umut verici bir yakla\u015f\u0131m, esnek \u00f6\u011frenen eylemlili\u011finin geli\u015fimini desteklemek i\u00e7in \u00f6\u011frenme s\u00fcrecinin \u00f6z\u00fcn\u00fc ve \u00e7e\u015fitli y\u00f6nlerini kapsar (Deakin Crick, Huang, Ahmed Shafi ve Goldspink, 2015). Di\u011fer bir yeni geli\u015fme, \u00f6\u011frencilere duygusal durumlar\u0131 hakk\u0131nda geri bildirim verilmesini i\u00e7erir. Grawemeyer vd. (2016), etki fark\u0131ndal\u0131\u011f\u0131 geri bildirimi alan \u00f6\u011frencilerin, sadece performanslar\u0131yla ilgili geri bildirim alan kar\u015f\u0131la\u015ft\u0131rmal\u0131 bir akran grubundan daha az s\u0131k\u0131ld\u0131\u011f\u0131n\u0131 ve g\u00f6revlerine daha tutarl\u0131 bir \u015fekilde ba\u011fl\u0131 oldu\u011funu belirtmi\u015flerdir. Temel olarak, yazarlar \u00f6\u011frenenin duygusal durumuna ili\u015fkin otomatik geri bildirim sa\u011flaman\u0131n kat\u0131l\u0131m ve g\u00f6rev yapma davran\u0131\u015f\u0131na yard\u0131mc\u0131 olabilece\u011fini g\u00f6stermektedir. Ruiz vd. (2016), \u00f6\u011frenen duygular\u0131 ve ders boyunca evrimleri hakk\u0131nda g\u00f6rsel geri bildirim sa\u011flayan g\u00f6rsel bir g\u00f6sterge panosu geli\u015ftirmi\u015ftir. Bu \u00f6rnekte, yazarlar \u00f6z bildirimli duygusal durumlar\u0131n performans\u0131 ve ders tasar\u0131mlar\u0131n\u0131 iyile\u015ftirmek i\u00e7in \u00f6z derin d\u00fc\u015f\u00fcnme kayna\u011f\u0131 olarak kulland\u0131lar. Bununla birlikte, bu \u00e7al\u0131\u015fmalar ayn\u0131 zamanda, herhangi bir ba\u015far\u0131n\u0131n b\u00fcy\u00fck \u00f6l\u00e7\u00fcde \u00f6\u011frenenlerin bu t\u00fcr \u00f6\u011frenme analiti\u011fi uygulamalar\u0131ndan gelen geri bildirimleri kullanarak \u00f6z y\u00f6netim yeterlili\u011fine ba\u011fl\u0131 oldu\u011funu g\u00f6stermektedir. Tasar\u0131m veya teknoloji olanaklar\u0131n\u0131 \u00f6\u011frenmenin \u00f6\u011frencinin derin d\u00fc\u015f\u00fcnmesini harekete ge\u00e7irmesi durumunda, \u00f6\u011frenenlerin varsay\u0131lan yetkinlik seviyesinin daha az esas al\u0131nd\u0131\u011f\u0131 tespit edilmi\u015ftir.. Di\u011fer bir deyi\u015fle, \u00f6\u011frenene ait d\u00fc\u015f\u00fcnce yazma metni veya ek a\u00e7\u0131klamalar (ayr\u0131ca video i\u00e7i) yaz\u0131larak d\u0131\u015fsalla\u015ft\u0131r\u0131l\u0131r ve bu yaz\u0131l\u0131 metne bi\u00e7imlendirici geri bildirim sunulabilir.<\/span><\/p>\n

                  Yaz\u0131l\u0131 metinler \u00fczerine, kompozisyon notland\u0131rman\u0131n \u00f6tesinde geri bildirim sa\u011flanmas\u0131, s\u00f6ylem merkezli analitik alan\u0131ndaki \u00e7e\u015fitli giri\u015fimlerle ele al\u0131nm\u0131\u015ft\u0131r (De Liddo, Buckingham Shum ve Quinto, 2011). Ayr\u0131ca, yazma analiti\u011fi olarak da adland\u0131r\u0131lan bu alan, \u00d6A \/ EVM topluluklar\u0131 aras\u0131nda g\u00fc\u00e7l\u00fc bir varl\u0131\u011fa sahiptir; otomatik metin analizi y\u00f6ntemleri, s\u00f6ylem analizi ve \u00f6\u011frenme veya bilgi in\u015fas\u0131n\u0131 g\u00f6steren yaz\u0131l\u0131 metni tan\u0131mlamak i\u00e7in kullan\u0131lan bilgi i\u015flemsel dilbilim aras\u0131nda \u00f6nemli bir \u00f6rt\u00fc\u015fme vard\u0131r. (\u00f6r. Simsek, Shum, De Liddo, Ferguson ve Sandor, 2014). K\u0131sacas\u0131, s\u00f6ylem merkezli analitik, bili\u015fsel kat\u0131l\u0131m\u0131n kalitesiyle ilgili olarak ya da \u00f6zellikle i\u00e7g\u00f6r\u00fc, t\u00fcr\u00fcn kalitesi vb. gibi bir alan becerisi olarak yazma hususlar\u0131na yard\u0131mc\u0131 olmak i\u00e7in geri bildirim sunar (\u00f6r. Crossley, Allen, Snow ve McNamara, 2015; Kar, Allen, Jacovina, Perret ve McNamara, 2015; Whitelock, Twiner, Richardson, Field ve Pulman, 2015). \u00d6A ara\u015ft\u0131rmalar\u0131nda dikkat \u00e7ekici bir \u015fekilde ortaya \u00e7\u0131kan bir e\u011filim, \u00f6\u011frenenin hem \u00f6\u011frenme i\u00e7eri\u011fi hem de s\u00fcreciyle bireysel olarak etkile\u015fime girme potansiyelini derinle\u015ftirmeye y\u00f6nelik bi\u00e7imlendirici geri bildirim sunan yans\u0131t\u0131c\u0131 yaz\u0131m\u0131n2<\/a><\/sup> analizini vurgulamaktad\u0131r (Buckingham Shum vd., 2016; Gibson ve Kitto, 2015).<\/span><\/p>\n\n

                  SONU\u00c7<\/h2>\n

                  Bu b\u00f6l\u00fcm, EVM ve \u00d6A topluluklar\u0131n\u0131n mevcut ara\u015ft\u0131rma alan\u0131 i\u00e7inde, \u00f6\u011frenen \u00f6\u011frenme deneyiminin kalitesi, geri bildirimin en etkili y\u00f6nlerinden birini konumland\u0131rm\u0131\u015ft\u0131r. Geri bildirim ve ki\u015fiselle\u015ftirilmi\u015f \u00f6\u011frenme aras\u0131ndaki do\u011frudan ba\u011flant\u0131ya ra\u011fmen, ele al\u0131nmas\u0131 gereken \u00f6nemli bo\u015fluklar vard\u0131r. Ara\u015ft\u0131rman\u0131n yetersizli\u011fi, \u00f6\u011frencilerin algoritma ile \u00fcretilen geri bildirimlerle nas\u0131l etkile\u015fime girdiklerini ve d\u00f6n\u00fc\u015ft\u00fcr\u00fcld\u00fcklerini ara\u015ft\u0131rmaktad\u0131r. Ayr\u0131ca, veri analizinden elde edilebilecek m\u00fcdahalelerin t\u00fcr\u00fc ile yeterli geri bildirim formlar\u0131 aras\u0131ndaki ili\u015fki yeterince ara\u015ft\u0131r\u0131lmam\u0131\u015ft\u0131r. \u00d6\u011frenme deneyimlerindeki geri bildirimlerin etkisini analiz eden \u00f6nemli bir literat\u00fcr olumlu birlikte \u00f6\u011frenme deneyimlerindeki teknoloji arac\u0131l\u0131\u011f\u0131yla t\u00fcretilen kapsaml\u0131 veri k\u00fcmeleri ile bu alan\u0131n tekrar g\u00f6zden ge\u00e7irilmesi gerekmektedir. Geleneksel y\u00fcz y\u00fcze ve karma \u00f6\u011frenme senaryolar\u0131nda, i\u015f y\u00fck\u00fcndeki art\u0131\u015f ve s\u0131n\u0131rl\u0131 \u00f6\u011freten zaman\u0131, \u00f6\u011frenciler taraf\u0131ndan al\u0131nan geri bildirimlerin kalitesini etkilemektedir. KA\u00c7D'ler gibi yeni ortaya \u00e7\u0131kan senaryolar, b\u00fcy\u00fck \u00f6\u011frenen topluluklar\u0131n\u0131n y\u00fcksek kalitede geri bildirim sa\u011flamada \u00f6nemli zorluklar do\u011furmaktad\u0131r. \u00d6A ve EVM, bu s\u0131n\u0131rlamalar\u0131n nas\u0131l ele al\u0131naca\u011f\u0131n\u0131 ve geri bildirimin hem \u00f6l\u00e7eklendirilebilir hem de etkili oldu\u011fu yeni paradigmalar\u0131 nas\u0131l \u00f6nerece\u011fini ara\u015ft\u0131r\u0131yor. Her iki topluluktaki giri\u015fimlerin geri bildirimlerle g\u00fc\u00e7l\u00fc bir ba\u011flant\u0131s\u0131 olmas\u0131na ra\u011fmen, her disiplin \u00e7\u00f6z\u00fcmlerini geli\u015ftirdi\u011fi odaklanma alanlar\u0131 a\u00e7\u0131s\u0131ndan farkl\u0131l\u0131klar g\u00f6stermektedir. Bu odaklar tamamlay\u0131c\u0131d\u0131r ve \u00e7o\u011fu zaman birbirlerine dayan\u0131rlar. Sonu\u00e7 olarak, her iki disiplin de genel bir \u00f6\u011frenme senaryosunda geri bildirimin oynad\u0131\u011f\u0131 rol\u00fcn, ilgili unsurlar\u0131n ve \u00f6\u011frencilerin bilgisinde, inan\u00e7lar\u0131nda ve tutumlar\u0131nda de\u011fi\u015fikliklere \u00f6nc\u00fcl\u00fck etmenin nihai amac\u0131ndan daha kapsaml\u0131 bir bak\u0131\u015f a\u00e7\u0131s\u0131ndan faydalanabilir. Her iki ara\u015ft\u0131rma toplulu\u011fundan uygulay\u0131c\u0131lar, disiplinler aras\u0131nda daha etkili bir entegrasyonun yan\u0131 s\u0131ra insan ve teknolojinin kombinasyonunu destekleyen geri bildirim i\u00e7in daha kapsaml\u0131 bir \u00e7er\u00e7eve benimsemekten de faydalanabilirler.<\/span><\/p>\n\n

                  KAYNAK\u00c7A<\/h2>\nAbbas, S., & Sawamura, H. (2009). Developing an argument learning environment using agent-based ITS (ALES). In T. Barnes, M. Desmarais, C. Romero, & S. Ventura (Eds.), Proceedings of the 2nd International Conference on Educational Data Mining <\/i>(EDM2009), 1\u20133 July 2009, Cordoba, Spain (pp. 200\u2013209). International Educational Data Mining Society. <\/span><\/span>\n\nAllen, L. K., & McNamara, D. S. (2015). You are your words: Modeling students\u2019 vocabulary knowledge with natural language processing tools. In O. C. Santos et al. (Eds.), Proceedings of the 8th International Conference on Educational Data Mining <\/i>(EDM2015), 26\u201329 June 2015, Madrid, Spain (pp. 258\u2013265). International Educational Data Mining Society. <\/span><\/span>\n\nArnold, K. E., Lonn, S., & Pistilli, M. D. (2014). An exercise in institutional reflection: The learning analytics readiness instrument (LARI). Proceedings of the 4th International Conference on Learning Analytics and Knowledge <\/i>(LAK\u201914), 24\u201328 March 2014, Indianapolis, IN, USA (pp. 163\u2013165). New York: ACM. doi:10.1145\/2567574.2567621 <\/span><\/span>\n\nArroyo, I., Meheranian, H., & Woolf, B. P. (2010). Effort-based tutoring: An empirical approach to intelligent tutoring. In R. S. J. d. Baker, A. Merceron, & P. I. Pavlik Jr. (Eds.), Proceedings of the 3rd International Conference on Educational Data Mining <\/i>(EDM2010), 11\u201313 June 2010, Pittsburgh, PA, USA (pp. 1\u201310). International Educational Data Mining Society.<\/span><\/span>\n\nBaepler, P., & Murdoch, C. J. (2010). Academic analytics and data mining in higher education. International Journal for the Scholarship of Teaching and Learning, 4<\/i>(2). doi:10.20429\/ijsotl.2010.040217 <\/span><\/span>\n\nBaker, R., & Inventado, P. S. (2014). Educational data mining and learning analytics. In J. A. Larusson & B. White (Eds.), Learning analytics: From research to practice (pp. 61\u201375). Springer. <\/span><\/span>\n\nBaker, R., & Siemens, G. (2014). Educational data mining and learning analytics. In R. K. Sawyer (Ed.), The Cambridge handbook of the learning sciences<\/i>. Cambridge University Press. <\/span><\/span>\n\nBakharia, A., Kitto, K., Pardo, A., Ga\u0161evi\u0107, D., & Dawson, S. (2016). Recipe for success: Lessons learnt from using xAPI within the connected learning analytics toolkit. Proceedings of the 6th International Conference on Learning Analytics and Knowledge <\/i>(LAK\u201916), 25\u201329 April 2016, Edinburgh, UK (pp. 378\u2013382). New York: ACM. <\/span><\/span>\n\nBarker-Plummer, D., Cox, R., & Dale, R. (2009). Dimensions of difficulty in translating natural language into first order logic. In T. Barnes, M. Desmarais, C. Romero, & S. Ventura (Eds.), Proceedings of the 2nd International Conference on Educational Data Mining <\/i>(EDM2009), 1\u20133 July 2009, Cordoba, Spain (pp. 220\u2013229). International Educational Data Mining Society. <\/span><\/span>\n\nBarker-Plummer, D., Cox, R., & Dale, R. (2011). Student translations of natural language into logic: The grade grinder corpus release 1.0. In M. Pechenizkiy, T. Calders, C. Conati, S. Ventura, C. Romero, & J. Stamper (Eds.), Proceedings of the 4th Annual Conference on Educational Data Mining <\/i>(EDM2011), 6\u20138 July 2011, Eindhoven, The Netherlands (pp. 51\u201360). International Educational Data Mining Society. <\/span><\/span>\n\nBeheshitha, S. S., Hatala, M., Ga\u0161evi\u0107, D., & Joksimovi\u0107, S. (2016). The role of achievement goal-orientations when studying effect of learning analytics visualisations. Proceedings of the 6th International Conference on Learning Analytics and Knowledge <\/i>(LAK\u201916), 25\u201329 April 2016, Edinburgh, UK (pp. 54\u201363). New York: ACM. <\/span><\/span>\n\nBen-Naim, D., Bain, M., & Marcus, N. (2009). A user-driven and data-driven approach for supporting teachers in reflection and adaptation of adaptive tutorials. In T. Barnes, M. Desmarais, C. Romero, & S. Ventura (Eds.), Proceedings of the 2nd International Conference on Educational Data Mining <\/i>(EDM2009), 1\u20133 July 2009, Cordoba, Spain (pp. 21\u201330). International Educational Data Mining Society. <\/span><\/span>\n\nBlack, P., & Wiliam, D. (1998). Assessment and classroom learning. Assessment in Education: Principles, Policy & Practice, 5<\/i>(1), 7\u201374. doi:10.1080\/0969595980050102 <\/span><\/span>\n\nBouchet, F., Azevedo, R., Kinnebrew, J. S., & Biswas, G. (2012). Identifying students\u2019 characteristic learning behaviors in an intelligent tutoring system fostering self-regulated learning. In K. Yacef, O. Za\u00efane, A. Hershkovitz, M. Yudelson, & J. Stamper (Eds.), Proceedings of the 5th International Conference on Educational Data Mining <\/i>(EDM2012), 19\u201321 June, 2012, Chania, Greece (pp. 65\u201372). International Educational Data Mining Society. <\/span><\/span>\n\nBoud, D. (2000). Sustainable assessment: Rethinking assessment for the learning society. Studies in Continuing Education, 22<\/i>(2), 151\u2013167. doi:10.1080\/713695728 <\/span><\/span>\n\nBoud, D., & Molloy, E. (2013). Rethinking models of feedback for learning: The challenge of design. Assessment & Evaluation in Higher Education, 38<\/i>(6), 698\u2013712. doi:10.1080\/02602938.2012.691462 <\/span><\/span>\n\nBrusilovsky, P. (1996). Methods and techniques of adaptive hypermedia. User Modeling and User-Adapted Interaction, 6<\/i>, 87\u2013129. <\/span><\/span>\n\nBuckingham Shum, S., Sandor, A., Goldsmith, R., Wang, X., Bass, R., & McWilliams, M. (2016). Reflecting on reflective writing analytics: Assessment challenges and iterative evaluation of a prototype tool. Proceedings of the 6th International Conference on Learning Analytics and Knowledge <\/i>(LAK\u201916), 25\u201329 April 2016, Edinburgh, UK (pp. 213\u2013222). New York: ACM. <\/span><\/span>\n\nBull, S., & Kay, J. (2016). SMILI : A framework for interfaces to learning data in open learner models, learning analytics and related fields. International Journal of Artificial Intelligence in Education, 26<\/i>(1), 293\u2013331. <\/span><\/span>\n\nButler, D. L., & Winne, P. H. (1995). Feedback and self-regulated learning: A theoretical synthesis. Review of Educational Research, 65<\/i>(3), 245\u2013281. <\/span><\/span>\n\nCampbell, J. P., DeBlois, P. B., & Oblinger, D. (2007). Academic analytics: A new tool for a new era. EDUCAUSE Review, 42<\/i>, 40\u201357.<\/span><\/span>\n\nCharleer, S., Klerkx, J., & Duval, E. (2015). Exploring inquiry-based learning analytics through interactive surfaces. Proceedings of the Workshop on Visual Aspects of Learning Analytics <\/i>(VISLA\u201915), 16\u201320 March 2015, Poughkeepsie, NY, USA. http:\/\/ceur-ws.org\/Vol-1518\/paper6.pdf <\/span><\/span>\n\nClow, D. (2012). The learning analytics cycle: Closing the loop effectively. Proceedings of the 2nd International Conference on Learning Analytics and Knowledge <\/i>(LAK\u201912), 29 April\u20132 May 2012, Vancouver, BC, Canada (pp. 134\u2013138). New York: ACM. doi:10.1145\/2330601.2330636 <\/span><\/span>\n\nClow, D. (2014). Data wranglers: Human interpreters to help close the feedback loop. Proceedings of the 4th International Conference on Learning Analytics and Knowledge <\/i>(LAK\u201914), 24\u201328 March 2014, Indianapolis, IN, USA (pp. 49\u201353). New York: ACM. doi:10.1145\/2567574.2567603 <\/span><\/span>\n\nCorbett, A. T., Koedinger, K. R., & Anderson, J. R. (1997). Intelligent tutoring systems. In M. Heander, T. K. Landauer, & P. Prabhu (Eds.), Handbook of human\u2013computer interaction <\/i>(2nd ed., pp. 849\u2013870): Elsevier Science B. V. <\/span><\/span>\n\nCorrin, L., & de Barba, P. (2015). How do students interpret feedback delivered via dashboards? Proceedings of the 5th International Conference on Learning Analytics and Knowledge <\/i>(LAK\u201915), 16\u201320 March 2015, Poughkeepsie, NY, USA (pp. 430\u2013431). New York: ACM. doi:10.1145\/2723576.2723662 <\/span><\/span>\n\nCrossley, S., Allen, L. K., Snow, E. L., & McNamara, D. S. (2015). Pssst\u2026 textual features\u2026 there is more to automatic essay scoring than just you! Proceedings of the 5th International Conference on Learning Analytics and Knowledge <\/i>(LAK\u201915), 16\u201320 March 2015, Poughkeepsie, NY, USA (pp. 203\u2013207). New York: ACM. doi:10.1145\/2723576.2723595 <\/span><\/span>\n\nCrossley, S., Kyle, K., McNamara, D. S., & Allen, L. (2014). The importance of grammar and mechanics in writing assessment and instruction: Evidence from data mining. In J. Stamper, Z. Pardos, M. Mavrikis, & B. M. McLaren (Eds.), Proceedings of the 7th International Conference on Educational Data Mining <\/i>(EDM2014), 4\u20137 July, London, UK (pp. 300\u2013303). International Educational Data Mining Society. <\/span><\/span>\n\nDawson, S. (2010). \u201cSeeing\u201d the learning community: An exploration of the development of a resource for monitoring online student networking. British Journal of Educational Technology, 41<\/i>(5), 736\u2013752. <\/span><\/span>\n\nDawson, S., Bakharia, A., & Heathcote, E. (2010). SNAPP: Realising the affordances of real-time SNA within networked learning environments. In L. Dirckinck-Holmfeld, V. Hodgson, C. Jones, M. de Laat, D. McConnell, & T. Ryberg (Eds.), Proceedings of the 7th International Conference on Networked Learning <\/i>(NLC 2010), 3\u20134 May 2010, Aalborg, Denmark. http:\/\/www.networkedlearningconference.org.uk\/past\/nlc2010\/abstracts\/ PDFs \/ Dawson.pdf <\/span><\/span>\n\nDe Liddo, A., Buckingham Shum, S., & Quinto, I. (2011). Discourse-centric learning analytics. Proceedings of the 1st International Conference on Learning Analytics and Knowledge <\/i>(LAK\u201911), 27 February\u20131 March 2011, Banff, AB, Canada (pp. 23\u201333). New York: ACM. <\/span><\/span>\n\nDeakin Crick, R., Huang, S., Ahmed Shafi, A., & Goldspink, C. (2015). Developing resilient agency in learning: The internal structure of learning power. British Journal of Educational Studies, 63<\/i>(2), 121\u2013160. doi: 10.1080 \/00071005.2015.1006574 <\/span><\/span>\n\nDeFalco, J. A., Baker, R., & D\u2019Mello, S. K. (2014). Addressing behavioral disengagement in online learning. Design recommendations for intelligent tutoring systems <\/i>(Vol. 2, pp. 49\u201356). Orlando, FL: U.S. Army Research Laboratory. <\/span><\/span>\n\nDominguez, A. K., Yacef, K., & Curran, J. R. (2010). Data mining for generating hints in a python tutor. In R. S. J. d. Baker, A. Merceron, & P. I. Pavlik Jr. (Eds.), Proceedings of the 3rd International Conference on Educational Data Mining <\/i>(EDM2010), 11\u201313 June 2010, Pittsburgh, PA, USA (pp. 91\u2013100). International Educational Data Mining Society. <\/span><\/span>\n\nEagle, M., & Barnes, T. (2013). Evaluation of automatically generated hint feedback. In S. K. D\u2019Mello, R. A. Calvo, & A. Olney (Eds.), Proceedings of the 6th International Conference on Educational Data Mining <\/i>(EDM2013), 6\u20139 July 2013, Memphis, TN, USA (pp. 372\u2013374). International Educational Data Mining Society\/Springer. <\/span><\/span>\n\nEagle, M., & Barnes, T. (2014). Data-driven feedback beyond next-step hints. In J. Stamper, Z. Pardos, M. Mavrikis, & B. M. McLaren (Eds.), Proceedings of the 7th International Conference on Educational Data Mining <\/i>(EDM2014), 4\u20137 July, London, UK (pp. 444\u2013446). International Educational Data Mining Society.<\/span><\/span>\n\nEvans, C. (2013). Making sense of assessment feedback in higher education. Review of Educational Research, 83<\/i>(1), 70\u2013120. doi:10.3102\/0034654312474350 <\/span><\/span>\n\nEzen-Can, A., & Boyer, K. E. (2013). Unsupervised classification of student dialogue acts with query-likelihood clustering. In S. K. D\u2019Mello, R. A. Calvo, & A. Olney (Eds.), Proceedings of the 6th International Conference on Educational Data Mining <\/i>(EDM2013), 6\u20139 July 2013, Memphis, TN, USA (pp. 20\u201327). International Educational Data Mining Society\/Springer. <\/span><\/span>\n\nEzen-Can, A., & Boyer, K. E. (2015). Choosing to interact: Exploring the relationship between learner personality, attitudes, and tutorial dialogue participation. In O. C. Santos et al. (Eds.), Proceedings of the 8th International Conference on Educational Data Mining <\/i>(EDM2015), 26\u201329 June 2015, Madrid, Spain (pp. 125\u2013128). International Educational Data Mining Society. <\/span><\/span>\n\nFancsali, S.E. (2014). Causal discovery with models: Behavior, affect, and learning in cognitive tutor algebra. In J. Stamper, Z. Pardos, M. Mavrikis, & B. M. McLaren (Eds.), Proceedings of the 7th International Conference on Educational Data Mining <\/i>(EDM2014), 4\u20137 July, London, UK (pp. 28\u201335). International Educational Data Mining Society. <\/span><\/span>\n\nFeng, M., Beck, J. E., & Heffernan, N. T. (2009). Using learning decomposition and bootstrapping with randomization to compare the impact of different educational interventions on learning. In T. Barnes, M. Desmarais, C. Romero, & S. Ventura (Eds.), Proceedings of the 2nd International Conference on Educational Data Mining <\/i>(EDM2009), 1\u20133 July 2009, Cordoba, Spain (pp. 51\u201360). International Educational Data Mining Society. <\/span><\/span>\n\nFerguson, R., & Buckingham Shum, S. (2012). Social learning analytics: Five approaches. Proceedings of the 2nd International Conference on Learning Analytics and Knowledge <\/i>(LAK\u201912), 29 April\u20132 May 2012, Vancouver, BC, Canada (pp. 23\u201333). New York: ACM. <\/span><\/span>\n\nGibson, A., & Kitto, K. (2015). Analysing reflective text for learning analytics: An approach using anomaly recontextualisation. Proceedings of the 5th International Conference on Learning Analytics and Knowledge <\/i>(LAK\u201915), 16\u201320 March 2015, Poughkeepsie, NY, USA (pp. 51\u201360). New York: ACM. doi:10.1145\/2723576.2723635 <\/span><\/span>\n\nGoldstein, P. J., & Katz, R. N. (2005). Academic analytics: The uses of management information and technology in higher education. Educause Center for Applied Research. <\/span><\/span>\n\nGraesser, A. C., Conley, M. W., & Olney, A. (2012). Intelligent tutoring systems. In K. R. Harris, S. Graham, & T. Urdan (Eds.), APA educational psychology handbook <\/i>(pp. 451\u2013473). American Psychological Association. <\/span><\/span>\n\nGrawemeyer, B., Mavrikis, M., Holmes, W., Guitierrez-Santos, S., Wiedmann, M., & Rummel, N. (2016). Affective off-task behaviour: How affect-aware feedback can improve student learning. Proceedings of the 6th International Conference on Learning Analytics and Knowledge <\/i>(LAK\u201916), 25\u201329 April 2016, Edinburgh, UK (pp. 104\u2013113). New York: ACM. <\/span><\/span>\n\nHattie, J. (2008). Visible learning: A synthesis of over 800 meta-analyses related to achievement. New York: Routledge. <\/span><\/span>\n\nHattie, J., & Timperley, H. (2007). The power of feedback. Review of Educational Research, 77<\/i>(1), 81\u2013112. doi:10.3102\/003465430298487 <\/span><\/span>\n\nHegazi, M. O., & Abugroon, M. A. (2016). The state of the art on educational data mining in higher education. International Journal of Computer Trends and Technology, 31<\/i>, 46\u201356. <\/span><\/span>\n\nHoward, L., Johnson, J., & Neitzel, C. (2010). Examining learner control in a structured inquiry cycle using process mining. In R. S. J. d. Baker, A. Merceron, & P. I. Pavlik Jr. (Eds.), Proceedings of the 3rd International Conference on Educational Data Mining <\/i>(EDM2010), 11\u201313 June 2010, Pittsburgh, PA, USA (pp. 71\u201380). International Educational Data Mining Society. <\/span><\/span>\n\nJeong, H., & Biswas, G. (2008). Mining student behavior models in learning-by-teaching environments. In R. S. J. d. Baker, T. Barnes, & J. E. Beck (Eds.), Proceedings of the 1st International Conference on Educational Data Mining <\/i>(EDM\u201908), 20\u201321 June 2008, Montreal, QC, Canada (pp. 127\u2013136). International Educational Data Mining Society. <\/span><\/span>\n\nJohnson, S., & Za\u00efane, O. R. (2012). Deciding on feedback polarity and timing. In K. Yacef, O. Za\u00efane, A. Hershkovitz, M. Yudelson, & J. Stamper (Eds.), Proceedings of the 5th International Conference on Educational Data Mining <\/i>(EDM2012), 19\u201321 June, 2012, Chania, Greece (pp. 220\u2013221). International Educational Data Mining Society. <\/span><\/span>\n\nKickmeier-Rust, M., Steiner, C. M., & Dietrich, A. (2015). Uncovering learning processes using competence-based knowledge structuring and Hasse diagrams. Proceedings of the Workshop on Visual Aspects of Learning Analytics <\/i>(VISLA\u201915), 16\u201320 March 2015, Poughkeepsie, NY, USA (pp. 36\u201340). <\/span><\/span>\n\nKinnebrew, J. S., & Biswas, G. (2012). Identifying learning behaviors by contextualizing differential sequence mining with action features and performance evolution. In K. Yacef, O. Za\u00efane, A. Hershkovitz, M. Yudelson, & J. Stamper (Eds.), Proceedings of the 5th International Conference on Educational Data Mining <\/i>(EDM2012), 19\u201321 June, 2012, Chania, Greece (pp. 57\u201364). International Educational Data Mining Society. <\/span><\/span>\n\nKluger, A. N., & DeNisi, A. (1996). The effects of feedback interventions on performance: A historical review, a meta-analysis, and a preliminary feedback intervention theory. Psychological Bulletin, 119<\/i>(2), 254\u2013284. <\/span><\/span>\n\nKobsa, A. (2007). Privacy-enhanced web personalization. In P. Brusilovsky, A. Kobsa, W. Nejdl (Eds.), The adaptive web: Methods and strategies of web personalization <\/i>(pp. 628\u2013670). Springer. doi:10.1007\/978-3-540- 72079-9_4. <\/span><\/span>\n\nKulhavy, R. W., & Stock, W. A. (1989). Feedback in written instruction: The place of response certitude. Educational Psychology Review, 1<\/i>(4), 279\u2013308. <\/span><\/span>\n\nLang, C., Heffernan, N., Ostrow, K., & Wang, Y. (2015). The impact of incorporating student confidence items into an intelligent tutor: A randomized controlled trial. In O. C. Santos et al. (Eds.), Proceedings of the 8th International Conference on Educational Data Mining <\/i>(EDM2015), 26\u201329 June 2015, Madrid, Spain (pp. 144\u2013149). International Educational Data Mining Society. <\/span><\/span>\n\nLewkow, N., Zimmerman, N., Riedesel, M., & Essa, A. (2015). Learning analytics platform: Towards an open scalable streaming solution for education. In O. C. Santos et al. (Eds.), Proceedings of the 8th International Conference on Educational Data Mining <\/i>(EDM2015), 26\u201329 June 2015, Madrid, Spain (pp. 460\u2013463). International Educational Data Mining Society. <\/span><\/span>\n\nLockyer, L., Heathcote, E., & Dawson, S. (2013). Informing pedagogical action: Aligning learning analytics with learning design. American Behavioral Scientist, 57<\/i>(10), 1439\u20131459. doi:10.1177\/0002764213479367 <\/span><\/span>\n\nLonn, S., Aguilar, S., & Teasley, S. D. (2013). Issues, challenges, and lessons learned when scaling up a learning analytics intervention. Proceedings of the 3rd International Conference on Learning Analytics and Knowledge <\/i>(LAK\u201913), 8\u201312 April 2013, Leuven, Belgium (pp. 235\u2013239). New York: ACM. doi:10.1145\/2460296.2460343 <\/span><\/span>\n\nLynch, C., Ashley, K. D., Aleven, V., & Pinkwart, N. (2008). Argument graph classification via genetic programming and C4.5. In R. S. J. d. Baker, T. Barnes, & J. E. Beck (Eds.), Proceedings of the 1st International Conference on Educational Data Mining <\/i>(EDM\u201908), 20\u201321 June 2008, Montreal, QC, Canada (pp. 137\u2013146). International Educational Data Mining Society. <\/span><\/span>\n\nMadhyastha, T. M., & Tanimoto, S. (2009). Student consistency and implications for feedback in online assessment systems. In T. Barnes, M. Desmarais, C. Romero, & S. Ventura (Eds.), Proceedings of the 2nd International Conference on Educational Data Mining <\/i>(EDM2009), 1\u20133 July 2009, Cordoba, Spain (pp. 81\u201390). International Educational Data Mining Society. <\/span><\/span>\n\nMavrikis, M. (2008). Data-driven modelling of students\u2019 interactions in an ILE. In R. S. J. d. Baker, T. Barnes, & J. E. Beck (Eds.), Proceedings of the 1st International Conference on Educational Data Mining <\/i>(EDM\u201908), 20\u201321 June 2008, Montreal, QC, Canada (pp. 87\u201396). International Educational Data Mining Society. <\/span><\/span>\n\nMcKay, T., Miller, K., & Tritz, J. (2012). What to do with actionable intelligence: E2Coach as an intervention engine. Proceedings of the 2nd International Conference on Learning Analytics and Knowledge <\/i>(LAK\u201912), 29 April\u20132 May 2012, Vancouver, BC, Canada (pp. 88\u201391). New York: ACM. doi:10.1145\/2330601.2330627 <\/span><\/span>\n\nMendiburo, M., Sulcer, B., & Hasselbring, T. (2014). Interaction design for improved analytics. Proceedings of the 4th International Conference on Learning Analytics and Knowledge <\/i>(LAK\u201914), 24\u201328 March 2014, Indianapolis, IN, USA (pp. 78\u201382). New York: ACM. doi:10.1145\/2567574.2567628 <\/span><\/span>\n\nMory, E. H. (2004). Feedback research revisited. In D. H. Jonassen (Ed.), Handbook of research on educational communication and technology <\/i>(Vol. 2, pp. 745\u2013783). Mahwah, NJ: Lawrence Erlbaum.<\/span><\/span>\n\nNicol, D., & Macfarlane-Dick, D. (2006). Formative assessment and self-regulated learning: A model and seven principles of good feedback practice. Studies in Higher Education, 31<\/i>(2), 199\u2013218. doi:10.1080\/03075070600572090 <\/span><\/span>\n\nOlsen, J. K., Aleven, V., & Rummel, N. (2015). Predicting student performance in a collaborative learning environment. In O. C. Santos et al. (Eds.), Proceedings of the 8th International Conference on Educational Data Mining <\/i>(EDM2015), 26\u201329 June 2015, Madrid, Spain (pp. 211\u2013217). International Educational Data Mining Society. <\/span><\/span>\n\nOstrow, K. S., & Heffernan, N. T. (2014). Testing the multimedia principle in the real world: A comparison of video vs. text feedback in authentic middle school math assignments. In J. Stamper, Z. Pardos, M. Mavrikis, & B. M. McLaren (Eds.), Proceedings of the 7th International Conference on Educational Data Mining <\/i>(EDM2014), 4\u20137 July, London, UK (pp. 296\u2013299). International Educational Data Mining Society. <\/span><\/span>\n\nPardo, A., Ellis, R. A., & Calvo, R. A. (2015). Combining observational and experiential data to inform the redesign of learning activities. Proceedings of the 5th International Conference on Learning Analytics and Knowledge <\/i>(LAK\u201915), 16\u201320 March 2015, Poughkeepsie, NY, USA (pp. 305\u2013309). New York: ACM. doi:10.1145\/2723576.2723625 <\/span><\/span>\n\nPardos, Z. A., Bergner, Y., Seaton, D. T., & Pritchard, D. E. (2013). Adapting Bayesian knowledge tracing to a massive open online course in edX. In S. K. D\u2019Mello, R. A. Calvo, & A. Olney (Eds.), Proceedings of the 6th International Conference on Educational Data Mining <\/i>(EDM2013), 6\u20139 July 2013, Memphis, TN, USA (pp. 137\u2013144). International Educational Data Mining Society\/Springer. <\/span><\/span>\n\nPechenizkiy, M., Calders, T., Vasilyeva, E., & De Bra, P. (2008). Mining the student assessment data: Lessons drawn from a small scale case study. In R. S. J. d. Baker, T. Barnes, & J. E. Beck (Eds.), Proceedings of the 1st International Conference on Educational Data Mining <\/i>(EDM\u201908), 20\u201321 June 2008, Montreal, QC, Canada (pp. 187\u2013191). International Educational Data Mining Society. <\/span><\/span>\n\nPechenizkiy, M., Trcka, N., Vasilyeva, E., van der Aalst, W., & De Bra, P. (2009). Process mining online assessment data. In T. Barnes, M. Desmarais, C. Romero, & S. Ventura (Eds.), Proceedings of the 2nd International Conference on Educational Data Mining <\/i>(EDM2009), 1\u20133 July 2009, Cordoba, Spain (pp. 279\u2013288). International Educational Data Mining Society. <\/span><\/span>\n\nPeddycord III, B., Hicks, A., & Barnes, T. (2014). Generating hints for programming problems using intermediate output. In J. Stamper, Z. Pardos, M. Mavrikis, & B. M. McLaren (Eds.), Proceedings of the 7th International Conference on Educational Data Mining <\/i>(EDM2014), 4\u20137 July, London, UK (pp. 92\u201398). International Educational Data Mining Society. <\/span><\/span>\n\nPiech, C., Huang, J., Chen, Z., Do, C., Ng, A., & Koller, D. (2013). Tuned models of peer assessment in MOOCs. In S. K. D\u2019Mello, R. A. Calvo, & A. Olney (Eds.), Proceedings of the 6th International Conference on Educational Data Mining <\/i>(EDM2013), 6\u20139 July 2013, Memphis, TN, USA (pp. 153\u2013160). International Educational Data Mining Society\/Springer. <\/span><\/span>\n\nPinkwart, N. (2016). Another 25 years of AIED? Challenges and opportunities for intelligent educational technologies of the future. International Journal of Artificial Intelligence in Education, 26<\/i>(2), 771\u2013783. doi:10.1007\/s40593-016-0099-7 <\/span><\/span>\n\nPintrich, P. R. (1999). The role of motivation in promoting and sustaining self-regulated learning. International Journal of Educational Research, 31<\/i>, 459\u2013470. doi:10.1016\/S0883-0355(99)00015-4 <\/span><\/span>\n\nRomero, C., & Ventura, S. (2013). Data mining in education. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 3<\/i>(1), 12\u201327. doi:10.1002\/widm.1075 <\/span><\/span>\n\nRuiz, S., Charleer, S., Urretavizcaya, M., Klerkx, J., Fernandez-Castro, I., & Duval, E. (2016). Supporting learning by considering emotions: Tracking and visualisation. A case study. Proceedings of the 6th International Conference on Learning Analytics and Knowledge <\/i>(LAK\u201916), 25\u201329 April 2016, Edinburgh, UK (pp. 254\u2013263). New York: ACM. doi:10.1145\/2883851.2883888 <\/span><\/span>\n\nShute, V. J. (2008). Focus on formative feedback. Review of Educational Research, 78<\/i>(1), 153\u2013189. doi:10.3102\/0034654307313795<\/span><\/span>\n\nSimsek, D., Shum, S. B., De Liddo, A., Ferguson, R., & S\u00e1ndor, \u00c1. (2014). Visual analytics of academic writing. Proceedings of the 4th International Conference on Learning Analytics and Knowledge <\/i>(LAK\u201914), 24\u201328 March 2014, Indianapolis, IN, USA (pp. 265\u2013266). New York: ACM. doi:10.1145\/2567574.2567577 <\/span><\/span>\n\nSnow, E. L., Allen, L. K., Jacovina, M. E., Perret, C. A., & McNamara, D. S. (2015). You\u2019ve got style: Detecting writing flexibility across time. Proceedings of the 5th International Conference on Learning Analytics and Knowledge <\/i>(LAK\u201915), 16\u201320 March 2015, Poughkeepsie, NY, USA (pp. 194\u2013202). New York: ACM. doi:10.1145\/2723576.2723592 <\/span><\/span>\n\nStefanescu, D., Rus, V., & Graesser, A. C. (2014). Towards assessing students\u2019 prior knowledge from tutorial dialogues. In J. Stamper, Z. Pardos, M. Mavrikis, & B. M. McLaren (Eds.), Proceedings of the 7th International Conference on Educational Data Mining <\/i>(EDM2014), 4\u20137 July, London, UK (pp. 197\u2013201). International Educational Data Mining Society. <\/span><\/span>\n\nSuthers, D., & Verbert, K. (2013). Learning analytics as a \u201cmiddle space.\u201d Proceedings of the 3rd International Conference on Learning Analytics and Knowledge <\/i>(LAK\u201913), 8\u201312 April 2013, Leuven, Belgium (pp. 1\u20134). New York: ACM. doi:10.1145\/2460296.2460298 <\/span><\/span>\n\nVerbert, K., Duval, E., Klerkx, J., Govaerts, S., & Santos, J. L. (2013). Learning analytics dashboard applications. American Behavioral Scientist, 57<\/i>(10), 1500\u20131509. <\/span><\/span>\n\nVerbert, K., Govaerts, S., Duval, E., Santos, J. L., Assche, F., Parra, G., & Klerkx, J. (2014). Learning dashboards: An overview and future research opportunities. Personal and Ubiquitous Computing, 18<\/i>(6), 1499\u20131514. doi:10.1007\/s00779-013-0751-2 <\/span><\/span>\n\nWen, M., Yang, D., & Ros\u00e9, C. P. (2014). Sentiment analysis in MOOC discussion forums: What does it tell us? In J. Stamper, Z. Pardos, M. Mavrikis, & B. M. McLaren (Eds.), Proceedings of the 7th International Conference on Educational Data Mining <\/i>(EDM2014), 4\u20137 July, London, UK (pp. 130\u2013137). International Educational Data Mining Society. <\/span><\/span>\n\nWhitelock, D., Twiner, A., Richardson, J. T. E., Field, D., & Pulman, S. (2015). OpenEssayist: A supply and demand learning analytics tool for drafting academic essays. Proceedings of the 5th International Conference on Learning Analytics and Knowledge <\/i>(LAK\u201915), 16\u201320 March 2015, Poughkeepsie, NY, USA (pp. 208\u2013212). New York: ACM. doi:10.1145\/2723576.2723599 <\/span><\/span>\n\nWiliam, D., Lee, C., Harrison, C., & Black, P. (2004). Teachers developing assessment for learning: Impact on student achievement. Assessment in Education: Principles, Policy & Practice, 11<\/i>(1), 49\u201365. doi:10.1080\/0969594042000208994 <\/span><\/span>\n\nWinne, P. H. (2014). Issues in researching self-regulated learning as patterns of events. Metacognition and Learning, 9<\/i>(2), 229\u2013237. doi:10.1007\/s11409-014-9113-3 <\/span><\/span>\n\nWinne, P. H., & Baker, R. (2013). The potentials of educational data mining for researching metacognition, motivation and self-regulated learning. Journal of Educational Data Mining, 5<\/i>(1), 1\u20138. <\/span><\/span>\n\nWise, A. F. (2014). Designing pedagogical interventions to support student use of learning analytics. Proceedings of the 4th International Conference on Learning Analytics and Knowledge <\/i>(LAK\u201914), 24\u201328 March 2014, Indianapolis, IN, USA (pp. 203\u2013211). New York: ACM. <\/span><\/span>\n\nZimmerman, B.J. (1990). Self-regulated learning and academic achievement: An overview. Educational Psychologist, 25(<\/i>1), 3\u201317. doi:10.1207\/s15326985ep2501_2<\/span><\/span>\n\n
                  \n\n
                  \n

                  1<\/a> orj. self\u2014 reflection<\/span><\/span><\/p>\n\n<\/div>\n

                  \n

                  2<\/a> orj. reflective writing<\/span><\/span><\/p>\n\n<\/div>\n","rendered":"

                  <\/a> Abelardo Pardo 1<\/sup>, Oleksandra Poquet 2<\/sup>, Roberto Martfnez \u2013 Maidonado 3<\/sup>, Shane Dawson2<\/sup><\/span><\/span><\/p>\n

                  1<\/sup> Bilgi \u0130leti\u015fim ve M\u00fchendislik Fak\u00fcltesi, Sidney \u00dcniversitesi,Avustralya<\/span><\/span><\/p>\n

                  2<\/sup>\u00d6\u011fretim \u0130novasyon Birimi, G\u00fcney Avustralya \u00dcniversitesi, Avustralya<\/span><\/span><\/p>\n

                  3<\/sup>Ba\u011flant\u0131sal Zek\u00e2 Merkezi, Teknoloji \u00dcniversitesi Sydney, Avustralya<\/span><\/span><\/p>\n

                  DOI: 10.18608\/hla17.014<\/span><\/span><\/p>\n

                  \u00d6Z<\/h2>\n

                  \u00d6\u011frenme analiti\u011fi (\u00d6A) ve e\u011fitsel veri madencili\u011fi (EVM) alanlar\u0131, \u00f6\u011frenme ortamlar\u0131 hakk\u0131ndaki bilgileri geli\u015ftirmek ve \u00f6\u011frencilerin genel deneyim kalitesini art\u0131rmak i\u00e7in verilerin kullan\u0131m\u0131n\u0131 ara\u015ft\u0131rmaktad\u0131r. Her iki disiplinin odak noktas\u0131, \u00f6\u011fretim tasar\u0131m\u0131, \u00f6zel ders verme, \u00f6\u011frenen ba\u015far\u0131s\u0131, duygusal esenlik vb. \u0130le ilgili geni\u015f bir yelpazeyi kapsar. Bu b\u00f6l\u00fcm, bu disiplinlerden elde edilen bilgileri, \u00f6\u011frencilere geri bildirim sa\u011flama konusundaki mevcut ara\u015ft\u0131rmalar ile birle\u015ftirme potansiyeline odaklanmaktad\u0131r. Geribildirim, bir \u00f6\u011frenme senaryosunda \u00f6nemli iyile\u015ftirme sa\u011flayabilecek fakt\u00f6rlerden biri olarak tan\u0131mlanm\u0131\u015ft\u0131r. Geri bildirimi karakterize eden sa\u011flam bir \u00e7al\u0131\u015fma toplulu\u011fu olmas\u0131na ra\u011fmen, \u00f6\u011frenenler hakk\u0131ndaki her yerde bulunan verilerin varl\u0131\u011f\u0131 ile bir araya gelmek, yeni veri odakl\u0131 \u00f6\u011frenen destek eylemlerini ke\u015ffetmek i\u00e7in verimli bir zemin sunar.<\/span><\/span><\/p>\n

                  Anahtar Kelimeler<\/span>: Uygulanabilir bilgi, geri bildirim, m\u00fcdahaleler, \u00f6\u011frenen destek eylemleri<\/span><\/span><\/p>\n

                  Son yirmi y\u0131l boyunca, e\u011fitim uygulamas\u0131 bir\u00e7ok cephede \u00f6nemli \u00f6l\u00e7\u00fcde de\u011fi\u015fmi\u015ftir. Buna e\u011fitim politikas\u0131ndaki de\u011fi\u015fimler de d\u00e2hildir, teknoloji zengini \u00f6\u011frenme alanlar\u0131n\u0131n ortaya \u00e7\u0131k\u0131\u015f\u0131, \u00f6\u011frenme teorisindeki geli\u015fmeler ve kalite g\u00fcvencesi ve de\u011ferlendirmesinin uygulanmas\u0131, bunlardan birka\u00e7\u0131d\u0131r. Bu de\u011fi\u015fikliklerin t\u00fcm\u00fc, \u00e7a\u011fda\u015f \u00f6\u011fretim uygulamas\u0131n\u0131n \u015fimdi nas\u0131l uyguland\u0131\u011f\u0131n\u0131 ve somutla\u015ft\u0131r\u0131ld\u0131\u011f\u0131n\u0131 etkilemi\u015ftir. E\u011fitim alan\u0131ndaki \u00e7ok say\u0131da paradigma kaymas\u0131na ra\u011fmen, \u00f6\u011frenenin \u00f6\u011frenmesini te\u015fvik etmede geri bildirimin kilit rol\u00fc, etkili \u00f6\u011fretim olarak kabul edilenler i\u00e7in temel olmaya devam etmi\u015ftir. Ayr\u0131ca, e\u011fitimin kitleselle\u015fmesiyle hem \u00f6\u011fretmenlere hem de \u00f6\u011frenenlere ger\u00e7ek zamanl\u0131 geri bildirim ve eyleme ge\u00e7irilebilir i\u00e7g\u00f6r\u00fcler sa\u011flama ihtiyac\u0131 giderek daha da artmaktad\u0131r. E\u011fitim dijital teknolojileri benimsedi\u011finden, bu t\u00fcr teknolojilerin kullan\u0131lmas\u0131n\u0131n \u00f6\u011frenenin \u00f6\u011frenmesine daha fazla yard\u0131mc\u0131 olaca\u011f\u0131, onlar\u0131 te\u015fvik edece\u011fi ve sosyo-k\u00fclt\u00fcrel ve ekonomik e\u015fitsizlikleri ele alaca\u011f\u0131na ili\u015fkin yayg\u0131n bir varsay\u0131m vard\u0131r. Bu pozitivist ideal, daha ki\u015fiselle\u015ftirilmi\u015f ve uyarlanabilir \u00f6\u011frenme yollar\u0131 olu\u015ftururken, e\u011fitime eri\u015filebilirli\u011fi art\u0131rmak i\u00e7in teknolojilerin benimsenebilece\u011fi fikrini yans\u0131tmaktad\u0131r.<\/span><\/p>\n

                  Bu ba\u011flamda, \u00f6\u011frenme analiti\u011fi (\u00d6A) ve e\u011fitsel veri madencili\u011fi (EVM) alanlar\u0131 e\u011fitim ile do\u011frudan ili\u015fkilidir. \u00d6A ve EVM, daha etkili \u00f6\u011fretim uygulamalar\u0131 geli\u015ftirmek i\u00e7in \u00f6\u011frenme s\u00fcre\u00e7lerini daha iyi anlamay\u0131 ama\u00e7lamaktad\u0131r (Baker ve Siemens, 2014). \u00d6\u011frencinin ilerlemesi hakk\u0131nda geri bildirim sa\u011flamak i\u00e7in \u00e7e\u015fitli teknolojilerle \u00f6\u011frenen etkile\u015fimlerinden geli\u015fen verilerin analizi, \u00d6A ve EVM \u00e7al\u0131\u015fmalar\u0131n\u0131n merkezinde yer alm\u0131\u015ft\u0131r. Bu b\u00f6l\u00fcmde, geri bildirimin \u00f6\u011frenenin \u00f6\u011frenmesini etkileyen en g\u00fc\u00e7l\u00fc itici g\u00fc\u00e7lerden biri oldu\u011funu savunuyoruz. Bu nedenle, \u00f6\u011frenme deneyiminin genel kalitesi, bir \u00f6\u011frenenin ald\u0131\u011f\u0131 geri bildirimin uygunlu\u011fu ve belirginli\u011fi ile derinden i\u00e7 i\u00e7edir. Ayr\u0131ca, geri bildirim sa\u011flama, de\u011ferlendirme yakla\u015f\u0131mlar\u0131 (Boud, 2000), \u00f6\u011frenme tasar\u0131m\u0131 (Lockyer, Heathcote ve Dawson, 2013) veya \u00f6\u011frenenlerin \u00f6z y\u00f6netimini te\u015fvik etme stratejileri gibi bir \u00f6\u011frenme deneyiminin di\u011fer y\u00f6nleriyle yak\u0131ndan ilgilidir. (Winne, 2014; Winne ve Baker, 2013). Bu b\u00f6l\u00fcmdeki tart\u0131\u015fman\u0131n \u00e7o\u011funlu\u011fu t\u00fcm e\u011fitim alanlar\u0131na uygulanabilse de inceleme a\u011f\u0131rl\u0131kl\u0131 olarak orta\u00f6\u011fretim sonras\u0131 e\u011fitim ve mesleki geli\u015fim \u00fczerine odaklanmaktad\u0131r.<\/span><\/p>\n

                  \u00d6\u011eRENMEDE VER\u0130 G\u00dcD\u00dcML\u00dc GER\u0130 B\u0130LD\u0130R\u0130M\u0130N ROL\u00dc<\/h2>\n

                  Geri bildirim ile ilgili tart\u0131\u015fmalar genellikle bir de\u011ferlendirme ve \u00f6\u011frenen ba\u015far\u0131s\u0131 etraf\u0131nda ger\u00e7ekle\u015fir (Black ve Wiliam, 1998; Boud, 2000). Bu ba\u011flamda, geri bildirimin birincil rol\u00fc, \u00f6\u011frenenin bir de\u011ferlendirme maddesinin tamamlanmas\u0131yla tespit edilen (alg\u0131lanan) a\u00e7\u0131klar\u0131 gidermesine yard\u0131mc\u0131 olmakt\u0131r. \u0130ronik olarak, de\u011ferlendirme puanlar\u0131 ve \u00f6\u011frenci ba\u015far\u0131s\u0131 verileri ayn\u0131 zamanda politik \u00f6ncelikleri ve g\u00fcndemleri y\u00f6nlendirmek i\u00e7in bir ara\u00e7 haline gelmi\u015ftir ve ayn\u0131 zamanda kalite g\u00fcvence \u015fartlar\u0131nda g\u00f6stergeler olarak kullan\u0131lmaktad\u0131r. \u00d6z\u00fcnde de\u011ferlendirme, kalite g\u00fcvencesini \u00f6l\u00e7mek ve rekabet\u00e7i s\u0131ralamalar\u0131 olu\u015fturmak i\u00e7in bir ara\u00e7 oldu\u011fu kadar, \u00f6\u011frenmeyi te\u015fvik etmek i\u00e7in kullan\u0131lan iki ucu keskin bir b\u0131\u00e7akt\u0131r (Wiliam, Lee, Harrison ve Black, 2004). Kalite g\u00fcvencesi i\u00e7in de\u011ferlendirmenin \u00f6nemini kabul ederken, \u00f6zellikle bi\u00e7imlendirici de\u011ferlendirme ile ilgili genellikle geri bildirimin de\u011ferine veya sadece belirlenmi\u015f \u00f6\u011frenme g\u00f6revlerini \u00f6\u011frenenin tamamlamas\u0131n\u0131n bir bile\u015feni olarak odaklan\u0131r\u0131z. Bu nedenle, bu b\u00f6l\u00fcm, geri bildirim mekanizmalar\u0131na odaklanarak de\u011ferlendirme uygulamalar\u0131n\u0131n \u00f6z\u00fcn\u00fcn d\u00f6n\u00fc\u015f\u00fcm\u00fcn\u00fc kolayla\u015ft\u0131rmak i\u00e7in \u00f6\u011frenen izleme verilerinden nas\u0131l yararlan\u0131labilece\u011fini ara\u015ft\u0131rmaktad\u0131r. Bu ama\u00e7la, \u00f6\u011frenme analiti\u011fi ve e\u011fitsel veri madencili\u011fi (\u00d6A \/ EVM) konusundaki ara\u015ft\u0131rmalar\u0131n geni\u015f kapsaml\u0131 bir \u00f6rne\u011fi ile \u00f6rneklenen veri ile geli\u015ftirilmi\u015f geri bildirimlerin yarat\u0131lmas\u0131 ve sunulmas\u0131na y\u00f6nelik mevcut yakla\u015f\u0131mlar\u0131 vurgulay\u0131p tart\u0131\u015f\u0131yoruz.<\/span><\/p>\n

                  Teorik Geribildirim Modelleri<\/h3>\n

                  E\u011fitim ba\u011flamlar\u0131nda birle\u015fik bir geri bildirim tan\u0131m\u0131 bulunmamakla birlikte, \u00f6\u011frenme \u00fczerindeki etkilerinin \u00e7e\u015fitli kapsaml\u0131 analizleri yap\u0131lm\u0131\u015ft\u0131r (\u00f6r. Evans, 2013; Hattie ve Timperley, 2007; Kluger ve DeNisi, 1996). \u00d6zetle, g\u00fc\u00e7l\u00fc g\u00f6rg\u00fcl\/deneysel kan\u0131tlar, geri bildirimin \u00f6\u011frenenin \u00f6\u011frenmesini etkileyen en g\u00fc\u00e7l\u00fc fakt\u00f6rlerden biri oldu\u011funu g\u00f6stermektedir (Hattie, 2008). \u00c7al\u0131\u015fmalar\u0131n \u00e7o\u011funlu\u011fu, geri bildirimin sa\u011flanmas\u0131n\u0131n akademik performans \u00fczerinde olumlu bir etkiye sahip oldu\u011fu sonucuna varm\u0131\u015ft\u0131r. Bununla birlikte, genel etki b\u00fcy\u00fckl\u00fc\u011f\u00fcn\u00fcn de\u011fi\u015fmesi ve baz\u0131 durumlarda olumsuz bir etkiye sahip oldu\u011fu kaydedilmi\u015ftir. \u00d6rne\u011fin, Kluger ve DeNisi (1996) taraf\u0131ndan yap\u0131lan bir \u00fcst analiz, yetersiz bir detay seviyesi veya verilen bilginin ilgisizli\u011fi ile karakterize edilen k\u00f6t\u00fc uygulanan geri bildirimlerin \u00f6\u011frenen performans\u0131 \u00fczerinde olumsuz bir etkisi olabilece\u011fini g\u00f6stermi\u015ftir. Bu durumda, yazarlar, \u00f6\u011frenenin geri bildirim oda\u011f\u0131 olan \u00fc\u00e7 d\u00fczey aras\u0131nda geri bildirime dikkat \u00e7ekmi\u015ftir: g\u00f6rev, g\u00fcd\u00fcleme ve \u00fcst g\u00f6rev seviyesi. \u00dc\u00e7\u00fc de e\u015fit derecede \u00f6nemlidir ve odakta kademeli olarak de\u011fi\u015febilir. Ek olarak, Shute (2008) geri bildirimi karma\u015f\u0131kl\u0131\u011f\u0131 ile ba\u011flant\u0131l\u0131 olarak s\u0131n\u0131fland\u0131rm\u0131\u015f ve olumsuz etki potansiyeli, hedef y\u00f6nelimi ile ba\u011flant\u0131, motivasyon, bili\u015fsel destek mekanizmalar\u0131ndaki varl\u0131\u011f\u0131, zamanlama veya farkl\u0131 \u00f6\u011frenen ba\u015far\u0131s\u0131 seviyeleri gibi geri bildirimin sa\u011flanmas\u0131n\u0131 etkileyen fakt\u00f6rleri analiz etmi\u015ftir. Shute, etkisini en \u00fcst d\u00fczeye \u00e7\u0131karmak i\u00e7in, bir \u00f6\u011frencinin eylemine cevap olarak verilen geri bildirimlerin, de\u011ferlendirme d\u0131\u015f\u0131, destekleyici, zaman\u0131nda ve \u00f6zel olmas\u0131 gerekti\u011fini belirtmi\u015ftir.<\/span><\/p>\n

                  \u00d6\u011frenmeyle geri bildirimi ili\u015fkilendiren erken modeller, b\u00fcy\u00fck \u00f6l\u00e7\u00fcde, \u00f6\u011frenciye sa\u011flanan bilgi t\u00fcrlerini tan\u0131mlamay\u0131 ama\u00e7lamaktad\u0131r. Temel olarak, bu \u00e7al\u0131\u015fmalar farkl\u0131 t\u00fcrdeki bilgilerin \u00f6\u011frencinin \u00f6\u011frenmesi \u00fczerine oynayabilece\u011fi etkiyi karakterize etmeye \u00e7al\u0131\u015fm\u0131\u015ft\u0131r (Kulhavy ve Stock, 1989). Geri bildirimin ilk kavramsalla\u015ft\u0131r\u0131lmas\u0131, \u00f6\u011frenmenin ger\u00e7ek ve istenen durumu aras\u0131ndaki a\u00e7\u0131\u011f\u0131n nas\u0131l kapanabilece\u011fine ili\u015fkin \u00f6\u011frenme biliminin kuramsalla\u015ft\u0131rmas\u0131ndaki farkl\u0131l\u0131klardan kaynaklanm\u0131\u015ft\u0131r (bk. Tarihsel inceleme, Kluger ve DeNisi, 1996; Mory, 2004). Mory (2004)\u2019e g\u00f6re, \u00e7a\u011fda\u015f modeller, \u00f6\u011frencilerin g\u00fc\u00e7l\u00fc bir beceri paketi kulland\u0131klar\u0131 g\u00f6revlerle me\u015fgul olma hallerinde oldu\u011fu gibi (Butler ve Winne, 1995) geri bildirimleri \u00f6z y\u00f6netimli \u00f6\u011frenme (\u00d6Y\u00d6) ba\u011flam\u0131nda g\u00f6ren eski paradigmalar \u00fczerine in\u015fa edilmi\u015ftir . Bu beceriler, hedeflerin belirlenmesi, stratejilerin d\u00fc\u015f\u00fcn\u00fclmesi, do\u011fru stratejilerin se\u00e7ilmesi ve bu stratejilerin hedeflere y\u00f6nelik ilerleme \u00fczerindeki etkilerinin izlenmesi, \u00f6\u011frencilerin ba\u015far\u0131s\u0131 ile ili\u015fkilidir (Butler ve Winne, 1995; Pintrich, 1999; Zimmerman, 1990). Geri bildirim ve \u00f6z y\u00f6netimli \u00f6\u011frenme aras\u0131ndaki teorik sentezlerinin bir par\u00e7as\u0131 olarak Butler ve Winne (1995, s. 248), modellerine iki geri besleme d\u00f6ng\u00fcs\u00fc yerle\u015ftirmi\u015ftir. \u0130lk d\u00f6ng\u00fc, bili\u015fsel sistem i\u00e7inde yer al\u0131r ve bireylerin kendi i\u00e7 bilgilerini ve inan\u00e7lar\u0131n\u0131, ama\u00e7lar\u0131n\u0131, taktiklerini ve stratejilerini izleme ve \u00f6\u011frenme senaryosunun gerektirdi\u011fi \u015fekilde de\u011fi\u015ftirmelerini sa\u011flar. \u0130kinci d\u00f6ng\u00fc, bir g\u00f6revle ilgilenen bir \u00f6\u011frenciden kaynaklanan \u00fcr\u00fcn \u00f6l\u00e7\u00fcl\u00fcrken ortaya \u00e7\u0131kar ve \u00f6\u011frenciye geri iletilen d\u0131\u015f geri bildirimin yarat\u0131lmas\u0131n\u0131 sa\u011flar; \u00f6rne\u011fin, bir de\u011ferlendirme puan\u0131 veya bir g\u00f6revin tamamlanmas\u0131 \u00fczerine yorum yapan bir \u00f6\u011freten.<\/span><\/p>\n

                  Hattie ve Timperley (2007) geri bildirim ve bunun ba\u015far\u0131ya olan etkisi \u00fczerine en etkili \u00e7al\u0131\u015fmalardan birini sa\u011flam\u0131\u015ft\u0131r. Yazarlar\u0131n kavramsal analizleri, bir \u00f6\u011frencinin performans\u0131 veya anlay\u0131\u015f\u0131 hakk\u0131nda bir arac\u0131 taraf\u0131ndan sa\u011flanan bilgiler olarak geri bildirim tan\u0131mlar\u0131 ile desteklenmi\u015ftir<\/i>. Yazarlar, kavram etraf\u0131nda dile getirilen herhangi bir geri bildirimin, \u00f6\u011frencinin mevcut anlay\u0131\u015f\u0131 ile istenen \u00f6\u011frenme hedefi aras\u0131ndaki uyu\u015fmazl\u0131\u011f\u0131 azaltmay\u0131 ama\u00e7lamas\u0131 gerekti\u011fi \u015feklinde bir geribildirim modeli \u00f6nermi\u015ftir. Bu nedenle, geribildirim \u00fc\u00e7 soru etraf\u0131nda \u00e7er\u00e7evelenebilir: nereye gidiyorum, nas\u0131l gidiyorum ve bundan sonra nereye olaca\u011f\u0131m? <\/i><\/span>Hattie ve Timperley (2007), bu sorular\u0131n her birinin d\u00f6rt farkl\u0131 seviyeye uygulanmas\u0131 gerekti\u011fini \u00f6nerdi: \u00f6\u011frenme g\u00f6revi, \u00f6\u011frenme s\u00fcreci, \u00f6z d\u00fczenleme ve ki\u015fi.<\/i><\/span> \u00d6\u011frenme g\u00f6revi seviyesi basit bir g\u00f6revin unsurlar\u0131n\u0131 ifade eder; \u00f6rne\u011fin, bir cevab\u0131n do\u011fru veya yanl\u0131\u015f olup olmad\u0131\u011f\u0131n\u0131 \u00f6\u011frenene bildirmek. \u00d6\u011frenme s\u00fcreci, farkl\u0131 zamanlarda \u00e7e\u015fitli g\u00f6revler i\u00e7eren genel \u00f6\u011frenme hedeflerini ifade eder. \u00d6z y\u00f6netim seviyesi, \u00f6\u011frenme hedefleri \u00fczerine derin d\u00fc\u015f\u00fcnme, do\u011fru stratejiyi se\u00e7me ve bu hedeflere do\u011fru ilerlemeyi izleme kapasitesini ifade eder. Son olarak, benlik d\u00fczeyi, \u00f6\u011frenme deneyimi ile ili\u015fkili olmayabilecek soyut ki\u015filik \u00f6zelliklerini ifade eder. S\u00fcre\u00e7 ve d\u00fczenleme seviyelerinin, derin \u00f6\u011frenmeyi ve g\u00f6rev ustal\u0131\u011f\u0131n\u0131 artt\u0131rmada en etkili oldu\u011fu iddia edilmektedir. G\u00f6rev seviyesinde geri bildirim, sadece \u00f6nceki iki seviyeye ek olarak etkilidir; \u00f6z d\u00fczeydeki geri bildirimin en az etkili oldu\u011fu g\u00f6sterilmi\u015ftir. Bu \u00fc\u00e7 soru ve d\u00f6rt geri bildirim seviyesi, geri bildirimi zamanlama, pozitif ve negatif iletiler (kutupluluk da denir) gibi di\u011fer y\u00f6nlerle ve ayn\u0131 zamanda bir de\u011ferlendirme arac\u0131n\u0131n bir par\u00e7as\u0131 olarak geri bildirimi d\u00e2hil etmenin sonu\u00e7lar\u0131 ile ba\u011flant\u0131 kurma hakk\u0131 sa\u011flar. Bu y\u00f6nlerin pozitif veya negatif olabilen birbirine ba\u011f\u0131ml\u0131 bir etkiye sahip oldu\u011fu g\u00f6sterilmi\u015ftir (Nicol ve Macfarlane-Dick, 2006).<\/span><\/p>\n

                  Yerle\u015fik geri bildirim modellerini incelerken, Boud ve Molloy (2013), genellikle kaynak k\u0131s\u0131tlamalar\u0131, \u00f6nerilen geri bildirim modelleri veya en az\u0131ndan her \u00f6\u011frencinin i\u00e7in de\u011ferlendirici, destekleyici, zaman\u0131nda ve \u00f6zel geri bildirim \u00fcretme mekanizmas\u0131n\u0131n elveri\u015fli olmayaca\u011f\u0131 veya en az\u0131ndan \u00e7a\u011fda\u015f e\u011fitim senaryolar\u0131 i\u00e7erisinde s\u00fcrd\u00fcr\u00fclebilir olmamas\u0131 nedeniyle zaman zaman \u00f6\u011frenciler ve e\u011fitim ortam\u0131 ile ilgili ger\u00e7ek\u00e7i olmayan varsay\u0131mlara dayand\u0131klar\u0131n\u0131 savunmu\u015flard\u0131r. Bu noktada, \u00d6A \/ EVM \u00e7al\u0131\u015fmas\u0131 geri bildirimlerin d\u00fczensiz ve tek y\u00f6nl\u00fc bir durumdan etkin birimler aras\u0131nda aktif bir diyaloga ta\u015f\u0131nmas\u0131nda \u00f6nemli bir rol oynayabilir.<\/span><\/p>\n

                  VER\u0130 DESTEKL\u0130 GER\u0130 B\u0130LD\u0130R\u0130M<\/h2>\n

                  \u00d6\u011frenmenin \u00f6zelliklerini geli\u015ftirmek i\u00e7in \u00e7ok miktarda veri kullanan ilk giri\u015fimler, uyarlanabilir hiper ortam<\/i><\/span> (Brusilovsky, 1996; Kobsa, 2007), ak\u0131ll\u0131 \u00f6\u011fretici sistemleri<\/i><\/span> (A\u00d6S’ler) (Corbett, Koedinger ve Anderson, 1997; Graesser, Conley ve Olney) ve akademik analitik (Baepler ve Murdoch, 2010; Campbell, DeBlois ve Oblinger, 2007; Goldstein ve Katz, 2005) gibi alanlara kadar dayand\u0131r\u0131labilir. Bu ara\u015ft\u0131rman\u0131n \u00e7o\u011fu, e\u011fitim uygulamalar\u0131n\u0131 ilerletmek amac\u0131yla, e\u011fitim ortam\u0131n\u0131n ara\u015ft\u0131r\u0131lmas\u0131na y\u00f6nelik veri yo\u011fun yakla\u015f\u0131mlara ortak ilgi duyan \u00d6A \/ EVM ara\u015ft\u0131rma topluluklar\u0131 i\u00e7erisinde ger\u00e7ekle\u015ftirilmi\u015ftir (Baker ve Inventado, 2014). Bu topluluklar\u0131n bir\u00e7ok benzerli\u011fi olsa da \u00d6A ve EVM aras\u0131nda baz\u0131 kabul edilmi\u015f farkl\u0131l\u0131klar vard\u0131r (Baker ve Siemens, 2014). \u00d6rne\u011fin, EVM, \u00d6A\u2019lar\u0131n b\u00fct\u00fcnsel sistemler i\u00e7inde yer alan insan liderli\u011findeki ara\u015ft\u0131rmalar\u0131n aksine, otomatik ke\u015fif y\u00f6ntemleri \u00fczerine daha indirgemeci bir odaklanmaya sahiptir. Baker ve Inventado (2014), \u00d6A ve EVM aras\u0131ndaki temel farkl\u0131l\u0131klar\u0131n, \u00e7o\u011funlukla tercih edilen metodolojilerde olmad\u0131\u011f\u0131n\u0131 ancak odakta, ara\u015ft\u0131rma sorular\u0131nda ve modellerin nihai kullan\u0131m\u0131nda oldu\u011funu belirtmi\u015ftir.<\/span><\/p>\n

                  \u00d6A \/ EVM’yi geri bildirim merce\u011fi arac\u0131l\u0131\u011f\u0131yla de\u011ferlendirirken, ara\u015ft\u0131rma yakla\u015f\u0131mlar\u0131 geri bildirimin y\u00f6n\u00fc ve al\u0131c\u0131s\u0131 ile ilgili olarak farkl\u0131l\u0131klar g\u00f6sterir. \u00d6rne\u011fin, \u00d6A giri\u015fimleri genel olarak \u00f6\u011freneni \u00f6\u011frenme s\u00fcrecinde geli\u015ftirmeye y\u00f6nelik geri bildirim sa\u011flar (\u00f6r. \u00f6z y\u00f6netim, hedef belirleme, motivasyon, stratejiler ve taktikler). Buna kar\u015f\u0131l\u0131k, EVM giri\u015fimleri, \u00f6\u011frenme ortam\u0131ndaki de\u011fi\u015fiklikleri ele almak i\u00e7in geri bildirim sa\u011flama konusuna odaklanma e\u011filimindedir (\u00f6r. bir g\u00f6revi de\u011fi\u015ftirecek ipu\u00e7lar\u0131 sa\u011flama, \u00e7evreyi ilgili kaynaklarla donatacak bulu\u015fsal y\u00f6ntemler vb.). Bu genellemelerin topluluklar\u0131n zor bir s\u0131n\u0131fland\u0131rmas\u0131 olmad\u0131\u011f\u0131n\u0131, daha ziyade \u00d6A \/ EVM \u00e7al\u0131\u015fmalar\u0131nda disiplin ge\u00e7mi\u015flerini ve ilgi alanlar\u0131n\u0131 yans\u0131tan g\u00f6zlemlenen bir e\u011filim oldu\u011funu not etmek \u00f6nemlidir. A\u015fa\u011f\u0131daki b\u00f6l\u00fcm, \u00f6\u011frenenlerin \u00f6\u011frenmelerine yard\u0131mc\u0131 olmak i\u00e7in geri bildirim sa\u011flama ile ilgili hem EVM hem de \u00d6A topluluklar\u0131ndaki \u00e7al\u0131\u015fmalar\u0131 daha da a\u00e7maktad\u0131r.<\/span><\/p>\n

                    \n
                  1. \n
                      \n
                    1. \n
                        \n
                      1. \n
                          \n
                        1. \n

                          E\u011fitsel Veri Madencili\u011finde Geribildirime Yakla\u015f\u0131mlar<\/h4>\n<\/li>\n<\/ol>\n<\/li>\n<\/ol>\n<\/li>\n<\/ol>\n<\/li>\n<\/ol>\n

                          EVM’de yap\u0131lan ara\u015ft\u0131rmalar, e\u011fitimde yapay zek\u00e2 (EYZ) ve ak\u0131ll\u0131 \u00f6\u011fretici sistemleri (A\u00d6S’ler) gibi disiplinlerle ba\u011flant\u0131l\u0131d\u0131r ve ili\u015fkilidir (Pinkwart, 2016). Geri bildirim s\u00fcre\u00e7leriyle ilgili olarak, \u00e7ok say\u0131da EVM ara\u015ft\u0131rma giri\u015fimi, uyarlanm\u0131\u015f ve ki\u015fiselle\u015ftirilmi\u015f geri bildirim veya \u00f6nerilerin \u00f6\u011frenenlere etkisini geli\u015ftirmek ve de\u011ferlendirmekle ilgilenmektedir (Hegazi ve Abugroon, 2016). Bu \u00e7al\u0131\u015fma, \u00f6\u011frenen modellemesi ve \/ veya tahmine dayal\u0131 modelleme ara\u015ft\u0131rmas\u0131na dayanmaktad\u0131r. Temel olarak, odak noktas\u0131, \u00f6\u011frencinin \u00f6zel ihtiya\u00e7lar\u0131na cevap vermek i\u00e7in geri bildirimin verilmesini sa\u011flayan \u00f6zel sistemler olu\u015fturmak, b\u00f6ylece \u00f6\u011frenmedeki geli\u015fmeleri kolayla\u015ft\u0131rmak, akademik performans\u0131 g\u00fc\u00e7lendirmek (olumlu) veya \u00f6\u011frencilerin belirli davran\u0131\u015flar\u0131 yerine getirmelerini engellemek olmu\u015ftur (Romero; Ventura, 2013).<\/span><\/p>\n

                          Geri bildirim sa\u011flama ile ilgilenen EVM yakla\u015f\u0131mlar\u0131, genel olarak baz\u0131 istisnalar d\u0131\u015f\u0131nda, g\u00f6rev d\u00fczeyinde geri bildirime vurgu yapm\u0131\u015ft\u0131r (\u00f6r. Arroyo, Meheranian ve Woolf, 2010; Kinnebrew ve Biswas, 2012; Lewkow, Zimmerman, Riedesel ve Essa, 2015; Madhyastha ve Tanimoto, 2009). EVM \u00fczerine yap\u0131lan erken ara\u015ft\u0131rmalar (bk. 2008 ve 2009’daki EVM konferans\u0131 bildirileri), veri odakl\u0131 modelleme (\u00f6r. Mavrikis, 2008), \u00f6\u011fretim g\u00f6revlileri (\u00f6r. Jeong) taraf\u0131ndan (\u00f6r. Jeong ve Biswas, 2008), talep \u00fczerine ve anl\u0131k bilgi istemlerinin sa\u011flanmas\u0131 (Lynch, Ashley, Aleven ve Pinkwart, 2008) de\u011ferlendirme g\u00f6revlerinin bir par\u00e7as\u0131 olarak ayr\u0131nt\u0131l\u0131 geri bildirim (Pechenizkiy, Calders, Vasilyeva ve De Bra, 2008), gecikmi\u015f geri bildirimi (Feng, Beck ve Heffernan, 2009) ve s\u00fcre\u00e7 modellemesi (Pechenizkiy, Trcka, Vasilyeva, van der Aalst ve De Bra, 2009) yoluyla \u00f6\u011frenenlere geri bildirim sa\u011flamay\u0131 ama\u00e7layan \u00e7ok \u00e7e\u015fitli yakla\u015f\u0131mlar ortaya koymu\u015ftur. Bu EVM \u00e7al\u0131\u015fmas\u0131, gelecekteki sistemleri bilgilendirmek i\u00e7in geri bildirim mekanizmalar\u0131n\u0131n ara\u00e7salla\u015ft\u0131r\u0131lmas\u0131 ve bu modellerin nas\u0131l geli\u015ftirilebilece\u011finin anla\u015f\u0131lmas\u0131 i\u00e7in ileriye d\u00f6n\u00fck \u00e7abalar\u0131 i\u00e7ermektedir. Ba\u015fka bir deyi\u015fle, algoritmalar potansiyel olarak daha iyi geri bildirim sa\u011flayan yeni sistemlerin tasar\u0131m\u0131n\u0131 etkileyecek teknik bilgi sa\u011flayabilir. \u00d6rne\u011fin, Barker-Plummer, Cox ve Dale (2009), daha iyi algoritmalar\u0131n sa\u011flanmas\u0131n\u0131n \u00f6tesine ge\u00e7me ve g\u00f6rev d\u00fczeyinde geri bildirimin epistemik ve pedagojik durumdan nas\u0131l etkilendi\u011fini anlama gere\u011fini \u00f6ne s\u00fcrd\u00fcler. Ba\u015fka bir deyi\u015fle, \u00f6\u011frenme s\u00fcrecindeki geri bildirim veya \u00f6z y\u00f6netim becerileri hakk\u0131ndaki bilgiler, g\u00f6rev d\u00fczeyinde geri bildirimin \u00e7er\u00e7eveye al\u0131nmas\u0131na yard\u0131mc\u0131 olabilir.<\/span><\/p>\n

                          Uyarlanabilir geri bildirim ile ilgili \u00e7al\u0131\u015fmalar\u0131n b\u00fcy\u00fck bir k\u0131sm\u0131 ak\u0131ll\u0131 \u00f6\u011fretici sistemleri (A\u00d6S’ler; \u00f6rne\u011fin, Abbas ve Sawamura, 2009; Eagle ve Barnes, 2013; Feng vd., 2009), \u00f6\u011frenme y\u00f6netim sistemleri (\u00d6YS; Dominguez, Yacef ve Curran, 2010; Lynch vd., 2008; Pechenizkiy vd., 2008) veya belirli bilgi alanlar\u0131ndaki \u00f6\u011frencilere bir dizi \u00f6\u011frenme g\u00f6revi sa\u011flayan e\u015fde\u011fer tek kullan\u0131c\u0131l\u0131 sistemler arac\u0131l\u0131\u011f\u0131 ile geli\u015ftirilmi\u015ftir. Bu sistemlerin \u00e7o\u011fu, \u00f6\u011frenen modellerini farkl\u0131 \u015fekillerde \u00e7eker: \u00f6rne\u011fin \u00f6\u011frenen davran\u0131\u015f\u0131n\u0131n izleri, bilgi, ba\u015far\u0131, bili\u015fsel durumlar veya duygusal durumlar. Bu modellere dayanarak, sistem genellikle sonraki ad\u0131m ipu\u00e7lar\u0131 gibi \u00e7e\u015fitli g\u00f6rev d\u00fczeyinde geri bildirim t\u00fcrleri sunar (\u00f6r. Peddycord, Hicks ve Barnes, 2014); bayrak geri bildirimi olarak da bilinen do\u011fruluk ipu\u00e7lar\u0131 (Barker \u2013 Plummer, Cox ve Dale, 2011); olumlu ya da cesaretlendirici ipu\u00e7lar\u0131 (Stefanescu, Rus ve Graesser, 2014); sonraki ad\u0131mlar veya g\u00f6revlerle ilgili \u00f6neriler (Ben-Naim, Bain ve Marcus, 2009); veya yukar\u0131dakilerin \u00e7e\u015fitli kombinasyonlar\u0131. Bu nedenle, davran\u0131\u015f modellemesi \u00fczerine yap\u0131lan \u00e7al\u0131\u015fmalar, EVM ara\u015ft\u0131rmalar\u0131nda otomatik geri bildirim s\u00fcre\u00e7leri geli\u015ftirmenin ayr\u0131lmaz bir par\u00e7as\u0131 olmu\u015ftur (DeFalco, Baker ve D\u2019Mello, 2014).<\/span><\/p>\n

                          Son y\u0131llarda, EVM’nin \u00f6\u011frenen modellemesindeki \u00e7al\u0131\u015fmas\u0131, ara\u015ft\u0131rmac\u0131lar\u0131n daha az yap\u0131land\u0131r\u0131lm\u0131\u015f \u00f6\u011frenme g\u00f6revleri i\u00e7in geri bildirim mekanizmalar\u0131 \u00fcretmelerine izin veren yeni y\u00f6ntemlerin ortaya \u00e7\u0131kmas\u0131yla zenginle\u015ftirilmi\u015ftir. Bir \u00f6rnek \u00f6\u011frenci yazma \u00e7al\u0131\u015fmas\u0131 bi\u00e7imlendirici ve \u00f6zetleyici geri bildirim sa\u011flamay\u0131 i\u00e7erir (Allen ve McNamara, 2015; Crossley, Kyle, McNamara ve Allen, 2014). Daha karma\u015f\u0131k alg\u0131lay\u0131c\u0131 cihazlar\u0131n ve tahmine dayal\u0131 algoritmalar\u0131n ortaya \u00e7\u0131kmas\u0131, g\u00fcven, tutum, ki\u015filik, motivasyon (Ezen-Can ve Boyer, 2015) ve etkileme gibi daha karma\u015f\u0131k be\u015feri boyutlar\u0131n\u0131n izlerini d\u00e2hil ederek \u00f6\u011frenen modellerinin geli\u015ftirilmesine olanak sa\u011flam\u0131\u015ft\u0131r (Fancsali, 2014). Bu daha farkl\u0131 veri yard\u0131mlar\u0131 her \u00f6\u011frenen i\u00e7in ki\u015fiselle\u015ftirilebilecek daha iyi cevap veren uyarlanabilir geri bildirim mekanizmalar\u0131n\u0131n geli\u015ftirilmesine yard\u0131mc\u0131 olur. \u00d6\u011frenci modellerinin karma\u015f\u0131kl\u0131\u011f\u0131na paralel olarak, baz\u0131 ara\u015ft\u0131rmac\u0131lar a\u00e7\u0131k \u00f6\u011frenen modelleme (A\u00d6M) kavram\u0131n\u0131 ara\u015ft\u0131rd\u0131lar (OLM; Bull ve Kay, 2016). A\u00d6M d\u00fc\u015f\u00fcncesi g\u00f6rsel veri sunumuna benzer ancak bir ara\u00e7 taraf\u0131ndan olu\u015fturulan modele uygulan\u0131r. A\u00d6M’ler EYZ toplulu\u011funda, tavsiyeler, d\u00fczeltici eylemler veya bir sonraki ad\u0131mla ilgili ipu\u00e7lar\u0131yla kar\u015f\u0131la\u015ft\u0131r\u0131ld\u0131\u011f\u0131nda daha az kuralc\u0131 geri bildirim bi\u00e7imleri sa\u011flama pe\u015finde ko\u015fmu\u015ftur. A\u00d6M’ler, kullan\u0131c\u0131n\u0131n (\u00f6\u011frenen, \u00f6\u011fretmen, akranlar, vb.) insan taraf\u0131ndan anla\u015f\u0131labilir formlarda sunulan \u00f6\u011frenen modelinin i\u00e7eri\u011fini g\u00f6r\u00fcnt\u00fclemesine ve yans\u0131tmas\u0131na (hatta incelemesine) izin verdi\u011fi i\u00e7in, yenilenmi\u015f ilgi g\u00f6rm\u00fc\u015ft\u00fcr. Bu modellerin avantajlar\u0131ndan biri, \u00f6\u011frenenlerin \u00f6z y\u00f6netim becerilerini yans\u0131tmas\u0131na ve te\u015fvik etmesine yard\u0131mc\u0131 olmakt\u0131r.<\/span><\/p>\n

                          Son zamanlarda, kitlesel a\u00e7\u0131k \u00e7evrimi\u00e7i derslerin artan pop\u00fclaritesi nedeniyle, bilimsel EVM \u00e7al\u0131\u015fmalar\u0131nda geri bildirimlerin art\u0131r\u0131lmas\u0131 g\u00fc\u00e7 kazand\u0131 (KA\u00c7D’ler; Wen, Yang ve Rose, 2014). KA\u00c7D’lerde (Pardos, Bergner, Seaton ve Pritchard, 2013) \u00f6\u011frenen \u00e7al\u0131\u015fmalar\u0131 i\u00e7in ki\u015fiselle\u015ftirilmi\u015f geri bildirim sa\u011flaman\u0131n yan\u0131 s\u0131ra, b\u00fcy\u00fck topluluklarda y\u00fcksek kalitede geri bildirime uygun eri\u015fim sa\u011flamak i\u00e7in mekanizma \u00fcretmeye de ilgi duyulmaktad\u0131r. Baz\u0131 geri bildirim \u00e7\u00f6z\u00fcmleri, karma\u015f\u0131k, a\u00e7\u0131k u\u00e7lu \u00f6\u011frenme g\u00f6revlerini video tabanl\u0131 geri bildirimler arac\u0131l\u0131\u011f\u0131yla (Ostrow ve Heffernan, 2014) veya akran geri bildirimleri \u00fczerine temellendirerek (Piech vd., 2013) ele almaktad\u0131r.<\/span><\/p>\n

                          EVM’de \u00f6\u011frencilere g\u00f6rev d\u00fczeyinde, ger\u00e7ek zamanl\u0131 geri bildirim sa\u011flama konusunda b\u00fcy\u00fck bir vurgu olmas\u0131na ra\u011fmen, di\u011fer yakla\u015f\u0131mlar da ara\u015ft\u0131r\u0131lm\u0131\u015ft\u0131r. \u00d6rne\u011fin, baz\u0131 \u00e7abalar \u00f6\u011frencilerin \u00f6\u011frenme s\u00fcrecindeki aksakl\u0131klar\u0131 \u00f6nlemek i\u00e7in gecikmeli geri bildirim sa\u011flamaya odaklanm\u0131\u015ft\u0131r (Feng vd., 2009; Johnson ve Zaiane, 2012). EVM’nin \u201cd\u00fczeltici\u201d geri bildirimin \u00f6tesine ge\u00e7mesi ve kutuplulu\u011fun (olumlu, olumsuz veya birle\u015fik geri bildirim) ve geri besleme zamanlamas\u0131n\u0131n \u00f6\u011frencilerin diyalo\u011funda (Ezen-Can ve Boyer, 2013), g\u00fcvende (Lang, Heffernan, Ostrow ve Wang, 2015) veya i\u015fbirlikli senaryolarda (Olsen, Aleven ve Rummel, 2015) oynayabilece\u011fi rol\u00fc anlamak da ilgi \u00e7ekmi\u015ftir. Sistematik olarak farkl\u0131 seviyelerde \u00f6\u011frenen faaliyetini hedefleyen geri bildirim sa\u011flama, baz\u0131 \u00f6rnekler sunulmu\u015f olsa da hen\u00fcz hak etti\u011fi ilgiyi g\u00f6rmemi\u015ftir. \u00d6rne\u011fin, Arroyo vd. (2010) ‘da dijital \u00f6\u011frenme yolda\u015f\u0131 bili\u015fsel (ipu\u00e7lar\u0131), duygusal (\u00f6vg\u00fc) ve \u00fcst bili\u015fsel seviyelerde (\u00f6r. ilerleme g\u00f6steren) geri bildirim veren akranlar olarak hareket etmi\u015ftir. G\u00f6rev d\u00fczeyinde bili\u015fsel seviye veya ipucu sa\u011flanmas\u0131 \u00f6nerildi. \u0130lerleme g\u00f6sterme, \u00f6z derin d\u00fc\u015f\u00fcnme1<\/a><\/sup> kapasitesine de\u011findi (yani bir hedefe y\u00f6nelik ilerlemeyi izlemek). \u00d6z y\u00f6netimli \u00f6\u011frenmeye y\u00f6nelik di\u011fer geri bildirim \u00f6rnekleri, \u00d6Y\u00d6 davran\u0131\u015f\u0131n\u0131 ve \u00f6z de\u011ferlendirmeyi desteklemeye (Bouchet, Azevedo, Kinnebrew ve Biswas, 2012); \u00fcst d\u00fczey \u00f6\u011frenci stratejilerini bili\u015fsel desteklemeye (Eagle ve Barnes, 2014); bilgi in\u015fas\u0131 stratejilerinin \u00f6nerilmesine (Kinnebrew ve Biswas, 2012) ve geri bildirimin \u00f6\u011frencilerin \u00f6\u011frenme s\u00fcre\u00e7lerinde nas\u0131l yer ald\u0131\u011f\u0131n\u0131 anlamaya (Howard, Johnson ve Neitzel, 2010) odaklanm\u0131\u015ft\u0131r.<\/span><\/p>\n

                            \n
                          1. \n
                              \n
                            1. \n
                                \n
                              1. \n
                                  \n
                                1. \n

                                  \u00d6\u011frenme Analiti\u011finde Geribildirime Yakla\u015f\u0131mlar<\/h4>\n<\/li>\n<\/ol>\n<\/li>\n<\/ol>\n<\/li>\n<\/ol>\n<\/li>\n<\/ol>\n

                                  Los Angeles’taki ara\u015ft\u0131rmada geri bildirime odaklanma genellikle \u00f6\u011frencinin \u00f6\u011frenme durumunu \u00e7e\u015fitli payda\u015flara, yani \u00f6\u011fretmenlere, \u00f6\u011frencilere veya y\u00f6neticilere iletme ihtiyac\u0131 olarak yorumlan\u0131r. \u0130lk \u00d6A ara\u015ft\u0131rmalar\u0131 (\u00f6r. LAK 2011 ve 2012 konferans\u0131 i\u015flemleri) kendi ba\u015f\u0131na geri bildirime odaklanmamas\u0131na kar\u015f\u0131n, \u00d6A’y\u0131 \u201charekete ge\u00e7irilebilir zek\u00e2\u201d \u00fcretmek i\u00e7in (McKay, Miller ve Tritz, 2012) \u00f6l\u00e7eklenebilir geri bildirim s\u00fcre\u00e7leriyle d\u00f6ng\u00fcy\u00fc kapatmas\u0131 gereken bir disiplin olarak vurgulam\u0131\u015ft\u0131r (Clow, 2012; Lonn, Aguilar ve Teasley, 2013). \u00d6A ara\u015ft\u0131rmalar\u0131, geri bildirimin, insanlara \u00f6\u011frenmenin eylemlilik ve do\u011fas\u0131na dair farkl\u0131 anlay\u0131\u015flar\u0131yla \u00e7ok say\u0131da disipline ait sesler arac\u0131l\u0131\u011f\u0131yla iletildi\u011fini kabul etmi\u015ftir (Suthers ve Verbert, 2013). Buna paralel olarak, Wise (2014) veri odakl\u0131 \u00f6\u011frenme m\u00fcdahalelerinin tasar\u0131m\u0131n\u0131, kendi sosyok\u00fclt\u00fcrel ba\u011flamlar\u0131nda nas\u0131l konumland\u0131klar\u0131n\u0131n fark\u0131ndal\u0131\u011f\u0131 ve \u00f6\u011frenen deste\u011fini ele alma amac\u0131 ile y\u00fcklemi\u015ftir. Ba\u011flam\u0131n \u00f6nemi nedeniyle, veri destekli geri bildirimin alg\u0131lanmas\u0131 ve yorumlanmas\u0131, \u00d6A geri bildirimi ile ilgili ara\u015ft\u0131rmalarda ayr\u0131 bir tema olmu\u015ftur. \u00d6A toplulu\u011fu, analitik ve payda\u015flar aras\u0131ndaki diyalogun ara\u015ft\u0131rmac\u0131lar taraf\u0131ndan \u00f6ng\u00f6r\u00fcld\u00fc\u011f\u00fc gibi ger\u00e7ekle\u015fmesini sa\u011flamak i\u00e7in kan\u0131t ve uygulamalar\u0131 ara\u015ft\u0131rm\u0131\u015ft\u0131r. \u00d6rne\u011fin, Corrin ve de Barba (2015) panolardaki \u00f6\u011frencilerin alg\u0131lar\u0131n\u0131 ara\u015ft\u0131rm\u0131\u015ft\u0131r; Beheshitha, Hatala, Ga\u0161evi\u0107 ve Joksimovi\u0107 (2016), farkl\u0131 ba\u015far\u0131 hedef y\u00f6nelimli \u00f6\u011frencilerin g\u00f6sterge panosu geri bildirimlerini ayn\u0131 \u015fekilde alg\u0131lay\u0131p alg\u0131lamad\u0131klar\u0131n\u0131 incelemi\u015ftir ve birka\u00e7 \u00e7al\u0131\u015fma, nitel g\u00f6r\u00fc\u015fmeleri veya insan yorumlay\u0131c\u0131lar\u0131n \u00e7al\u0131\u015fmalar\u0131n\u0131 veri odakl\u0131 analizlerle birle\u015ftirerek daha verimli bir ara\u015ft\u0131rma yapman\u0131n yollar\u0131n\u0131 konu edinmi\u015ftir (Arnold, Lonn ve Pistilli, 2014; Clow, 2014; Mendiburo, Sulcer ve Hasselbring, 2014; Pardo, Ellis ve Calvo, 2015). \u00d6\u011frencilerin bir t\u00fcr \u00f6zete veya etkinliklerinin g\u00f6stergelerine maruz b\u0131rak\u0131lmas\u0131, Hattie ve Timperley (2007) taraf\u0131ndan \u00f6nerilen taksonomide somut bir geri bildirim d\u00fczeyi ile ili\u015fkilendirilemez. Bununla birlikte, g\u00f6sterge panelleri genellikle g\u00f6rev d\u00fczeyinde bilgiler i\u00e7erir, \u00e7\u00fcnk\u00fc \u00f6\u011frenme s\u00fcreci veya \u00f6z y\u00f6netim becerileri hakk\u0131nda bilgi edinmek \u00e7ok daha zordur.<\/span><\/p>\n

                                  EVM’ye benzer \u015fekilde, \u00d6A toplulu\u011funun ilgisi, Hattie ve Timperley (2007) taraf\u0131ndan \u00f6nerilen taksonomideki \u00fc\u00e7\u00fcnc\u00fc seviye olan \u00f6z-izleme ve \u00f6z y\u00f6netim s\u00fcre\u00e7leri i\u00e7in \u00f6\u011frenenlere otomatik, \u00f6l\u00e7eklendirilmi\u015f ve ger\u00e7ek zamanl\u0131 geri bildirim sa\u011flamakt\u0131r. Bu y\u00f6nlendirme, g\u00f6rselle\u015ftirme, yans\u0131tma ve fark\u0131ndal\u0131k i\u00e7in ara\u00e7lar olarak \u00d6A uygulamalar\u0131n\u0131n istikrarl\u0131 bir \u015fekilde b\u00fcy\u00fcmesiyle elde edilmi\u015ftir (\u00f6r. Verbert, Duval, Klerkx, Govaerts ve Santos, 2013; Verbert vd., 2014). \u00d6zel g\u00f6rev d\u00fczeyinde geri bildirimler, EVM \/ A\u00d6S yakla\u015f\u0131mlar\u0131ndan daha az \u00f6n planda olsa da \u00d6A geri bildirimi yorumlama ve harekete kat\u0131lan insan-eylemlili\u011finin daha \u00e7ok \u00fczerinde durur. \u00d6A, \u00f6\u011frenme etkinliklerinin izlerini g\u00f6rselle\u015ftirerek s\u00fcre\u00e7 d\u00fczeyinde geri bildirimleri te\u015fvik etme e\u011filimindedir. \u00d6rne\u011fin, \u00f6\u011frenme g\u00f6sterge panelleri, \u00f6\u011frenenlerin hedefleri tan\u0131mlamas\u0131n\u0131 ve bu hedeflere do\u011fru ilerlemeyi izlemesini sa\u011flamak i\u00e7in harcanan zaman, kullan\u0131lan kaynaklar veya sosyal etkile\u015fim gibi veri kaynaklar\u0131n\u0131 yakalar (bk. Verbert vd., 2014). \u00d6\u011frenme g\u00f6sterge panolar\u0131n\u0131n son uygulamalar\u0131 zaman say\u0131s\u0131ndan veya \u00f6\u011frenme ile ilgili nesnelerin kullan\u0131lmas\u0131ndan kavramsalla\u015ft\u0131r\u0131lm\u0131\u015f bir s\u00fcre\u00e7le ilgili ilerlemeyi g\u00f6rselle\u015ftirmeye, \u00f6rne\u011fin sorgulamaya dayal\u0131 \u00f6\u011frenmeye y\u00f6nelik masa \u00fcst\u00fc g\u00f6rselle\u015ftirmelere (Charleer, Klerkx ve Duval, 2015), ya da yeterlilik grafikleri i\u00e7indeki \u00f6\u011frenme yollar\u0131n\u0131n g\u00f6rselle\u015ftirmelerine kayd\u0131rmaktad\u0131r(Kickmeier-Rust, Steiner ve Dietrich, 2015). Sosyal \u00f6\u011frenme analiti\u011finin bir par\u00e7as\u0131 olarak sosyal a\u011f analizi (Dawson, 2010; Dawson, Bakharia ve Heathcote, 2010) taraf\u0131ndan yap\u0131lan g\u00f6rselle\u015ftirmeler (\u00f6r. Ferguson ve Buckingham Shum, 2012), sosyal etkile\u015fim s\u00fcreci hakk\u0131nda pop\u00fcler bir geri bildirim t\u00fcr\u00fcd\u00fcr. Bunlar yak\u0131n zamanda \u00f6\u011frenenlerin, kiminle konu\u015ftuklar\u0131 \u00fczerine derin d\u00fc\u015f\u00fcnmelerini veya \u201cvah\u015fi do\u011fada\u201dki \u00f6\u011frenen a\u011flar\u0131nda, yani Twitter ya da Facebook gibi da\u011f\u0131t\u0131lm\u0131\u015f sosyal medyada ve \u00d6YS lerin \u00f6tesinde nerede konumland\u0131klar\u0131 konular\u0131na da geni\u015fletilmi\u015ftir (\u00f6r. Kitto, Pardo, Gasevi\u00e7 ve Dawson, 2016). Bu t\u00fcr a\u011f g\u00f6rselle\u015ftirmeleri, gruplara kolektif bilgi in\u015fas\u0131n\u0131n temsili olarak da sunulmu\u015ftur.<\/span><\/p>\n

                                  \u00d6\u011frencinin \u00f6z y\u00f6netimli \u00f6\u011frenme yeterlili\u011fini geli\u015ftirmeye y\u00f6nelik geri bildirim, ba\u015flang\u0131\u00e7 a\u015famas\u0131ndad\u0131r. Bi\u00e7imlendirici geri bildirime umut verici bir yakla\u015f\u0131m, esnek \u00f6\u011frenen eylemlili\u011finin geli\u015fimini desteklemek i\u00e7in \u00f6\u011frenme s\u00fcrecinin \u00f6z\u00fcn\u00fc ve \u00e7e\u015fitli y\u00f6nlerini kapsar (Deakin Crick, Huang, Ahmed Shafi ve Goldspink, 2015). Di\u011fer bir yeni geli\u015fme, \u00f6\u011frencilere duygusal durumlar\u0131 hakk\u0131nda geri bildirim verilmesini i\u00e7erir. Grawemeyer vd. (2016), etki fark\u0131ndal\u0131\u011f\u0131 geri bildirimi alan \u00f6\u011frencilerin, sadece performanslar\u0131yla ilgili geri bildirim alan kar\u015f\u0131la\u015ft\u0131rmal\u0131 bir akran grubundan daha az s\u0131k\u0131ld\u0131\u011f\u0131n\u0131 ve g\u00f6revlerine daha tutarl\u0131 bir \u015fekilde ba\u011fl\u0131 oldu\u011funu belirtmi\u015flerdir. Temel olarak, yazarlar \u00f6\u011frenenin duygusal durumuna ili\u015fkin otomatik geri bildirim sa\u011flaman\u0131n kat\u0131l\u0131m ve g\u00f6rev yapma davran\u0131\u015f\u0131na yard\u0131mc\u0131 olabilece\u011fini g\u00f6stermektedir. Ruiz vd. (2016), \u00f6\u011frenen duygular\u0131 ve ders boyunca evrimleri hakk\u0131nda g\u00f6rsel geri bildirim sa\u011flayan g\u00f6rsel bir g\u00f6sterge panosu geli\u015ftirmi\u015ftir. Bu \u00f6rnekte, yazarlar \u00f6z bildirimli duygusal durumlar\u0131n performans\u0131 ve ders tasar\u0131mlar\u0131n\u0131 iyile\u015ftirmek i\u00e7in \u00f6z derin d\u00fc\u015f\u00fcnme kayna\u011f\u0131 olarak kulland\u0131lar. Bununla birlikte, bu \u00e7al\u0131\u015fmalar ayn\u0131 zamanda, herhangi bir ba\u015far\u0131n\u0131n b\u00fcy\u00fck \u00f6l\u00e7\u00fcde \u00f6\u011frenenlerin bu t\u00fcr \u00f6\u011frenme analiti\u011fi uygulamalar\u0131ndan gelen geri bildirimleri kullanarak \u00f6z y\u00f6netim yeterlili\u011fine ba\u011fl\u0131 oldu\u011funu g\u00f6stermektedir. Tasar\u0131m veya teknoloji olanaklar\u0131n\u0131 \u00f6\u011frenmenin \u00f6\u011frencinin derin d\u00fc\u015f\u00fcnmesini harekete ge\u00e7irmesi durumunda, \u00f6\u011frenenlerin varsay\u0131lan yetkinlik seviyesinin daha az esas al\u0131nd\u0131\u011f\u0131 tespit edilmi\u015ftir.. Di\u011fer bir deyi\u015fle, \u00f6\u011frenene ait d\u00fc\u015f\u00fcnce yazma metni veya ek a\u00e7\u0131klamalar (ayr\u0131ca video i\u00e7i) yaz\u0131larak d\u0131\u015fsalla\u015ft\u0131r\u0131l\u0131r ve bu yaz\u0131l\u0131 metne bi\u00e7imlendirici geri bildirim sunulabilir.<\/span><\/p>\n

                                  Yaz\u0131l\u0131 metinler \u00fczerine, kompozisyon notland\u0131rman\u0131n \u00f6tesinde geri bildirim sa\u011flanmas\u0131, s\u00f6ylem merkezli analitik alan\u0131ndaki \u00e7e\u015fitli giri\u015fimlerle ele al\u0131nm\u0131\u015ft\u0131r (De Liddo, Buckingham Shum ve Quinto, 2011). Ayr\u0131ca, yazma analiti\u011fi olarak da adland\u0131r\u0131lan bu alan, \u00d6A \/ EVM topluluklar\u0131 aras\u0131nda g\u00fc\u00e7l\u00fc bir varl\u0131\u011fa sahiptir; otomatik metin analizi y\u00f6ntemleri, s\u00f6ylem analizi ve \u00f6\u011frenme veya bilgi in\u015fas\u0131n\u0131 g\u00f6steren yaz\u0131l\u0131 metni tan\u0131mlamak i\u00e7in kullan\u0131lan bilgi i\u015flemsel dilbilim aras\u0131nda \u00f6nemli bir \u00f6rt\u00fc\u015fme vard\u0131r. (\u00f6r. Simsek, Shum, De Liddo, Ferguson ve Sandor, 2014). K\u0131sacas\u0131, s\u00f6ylem merkezli analitik, bili\u015fsel kat\u0131l\u0131m\u0131n kalitesiyle ilgili olarak ya da \u00f6zellikle i\u00e7g\u00f6r\u00fc, t\u00fcr\u00fcn kalitesi vb. gibi bir alan becerisi olarak yazma hususlar\u0131na yard\u0131mc\u0131 olmak i\u00e7in geri bildirim sunar (\u00f6r. Crossley, Allen, Snow ve McNamara, 2015; Kar, Allen, Jacovina, Perret ve McNamara, 2015; Whitelock, Twiner, Richardson, Field ve Pulman, 2015). \u00d6A ara\u015ft\u0131rmalar\u0131nda dikkat \u00e7ekici bir \u015fekilde ortaya \u00e7\u0131kan bir e\u011filim, \u00f6\u011frenenin hem \u00f6\u011frenme i\u00e7eri\u011fi hem de s\u00fcreciyle bireysel olarak etkile\u015fime girme potansiyelini derinle\u015ftirmeye y\u00f6nelik bi\u00e7imlendirici geri bildirim sunan yans\u0131t\u0131c\u0131 yaz\u0131m\u0131n2<\/a><\/sup> analizini vurgulamaktad\u0131r (Buckingham Shum vd., 2016; Gibson ve Kitto, 2015).<\/span><\/p>\n

                                  SONU\u00c7<\/h2>\n

                                  Bu b\u00f6l\u00fcm, EVM ve \u00d6A topluluklar\u0131n\u0131n mevcut ara\u015ft\u0131rma alan\u0131 i\u00e7inde, \u00f6\u011frenen \u00f6\u011frenme deneyiminin kalitesi, geri bildirimin en etkili y\u00f6nlerinden birini konumland\u0131rm\u0131\u015ft\u0131r. Geri bildirim ve ki\u015fiselle\u015ftirilmi\u015f \u00f6\u011frenme aras\u0131ndaki do\u011frudan ba\u011flant\u0131ya ra\u011fmen, ele al\u0131nmas\u0131 gereken \u00f6nemli bo\u015fluklar vard\u0131r. Ara\u015ft\u0131rman\u0131n yetersizli\u011fi, \u00f6\u011frencilerin algoritma ile \u00fcretilen geri bildirimlerle nas\u0131l etkile\u015fime girdiklerini ve d\u00f6n\u00fc\u015ft\u00fcr\u00fcld\u00fcklerini ara\u015ft\u0131rmaktad\u0131r. Ayr\u0131ca, veri analizinden elde edilebilecek m\u00fcdahalelerin t\u00fcr\u00fc ile yeterli geri bildirim formlar\u0131 aras\u0131ndaki ili\u015fki yeterince ara\u015ft\u0131r\u0131lmam\u0131\u015ft\u0131r. \u00d6\u011frenme deneyimlerindeki geri bildirimlerin etkisini analiz eden \u00f6nemli bir literat\u00fcr olumlu birlikte \u00f6\u011frenme deneyimlerindeki teknoloji arac\u0131l\u0131\u011f\u0131yla t\u00fcretilen kapsaml\u0131 veri k\u00fcmeleri ile bu alan\u0131n tekrar g\u00f6zden ge\u00e7irilmesi gerekmektedir. Geleneksel y\u00fcz y\u00fcze ve karma \u00f6\u011frenme senaryolar\u0131nda, i\u015f y\u00fck\u00fcndeki art\u0131\u015f ve s\u0131n\u0131rl\u0131 \u00f6\u011freten zaman\u0131, \u00f6\u011frenciler taraf\u0131ndan al\u0131nan geri bildirimlerin kalitesini etkilemektedir. KA\u00c7D’ler gibi yeni ortaya \u00e7\u0131kan senaryolar, b\u00fcy\u00fck \u00f6\u011frenen topluluklar\u0131n\u0131n y\u00fcksek kalitede geri bildirim sa\u011flamada \u00f6nemli zorluklar do\u011furmaktad\u0131r. \u00d6A ve EVM, bu s\u0131n\u0131rlamalar\u0131n nas\u0131l ele al\u0131naca\u011f\u0131n\u0131 ve geri bildirimin hem \u00f6l\u00e7eklendirilebilir hem de etkili oldu\u011fu yeni paradigmalar\u0131 nas\u0131l \u00f6nerece\u011fini ara\u015ft\u0131r\u0131yor. Her iki topluluktaki giri\u015fimlerin geri bildirimlerle g\u00fc\u00e7l\u00fc bir ba\u011flant\u0131s\u0131 olmas\u0131na ra\u011fmen, her disiplin \u00e7\u00f6z\u00fcmlerini geli\u015ftirdi\u011fi odaklanma alanlar\u0131 a\u00e7\u0131s\u0131ndan farkl\u0131l\u0131klar g\u00f6stermektedir. Bu odaklar tamamlay\u0131c\u0131d\u0131r ve \u00e7o\u011fu zaman birbirlerine dayan\u0131rlar. Sonu\u00e7 olarak, her iki disiplin de genel bir \u00f6\u011frenme senaryosunda geri bildirimin oynad\u0131\u011f\u0131 rol\u00fcn, ilgili unsurlar\u0131n ve \u00f6\u011frencilerin bilgisinde, inan\u00e7lar\u0131nda ve tutumlar\u0131nda de\u011fi\u015fikliklere \u00f6nc\u00fcl\u00fck etmenin nihai amac\u0131ndan daha kapsaml\u0131 bir bak\u0131\u015f a\u00e7\u0131s\u0131ndan faydalanabilir. Her iki ara\u015ft\u0131rma toplulu\u011fundan uygulay\u0131c\u0131lar, disiplinler aras\u0131nda daha etkili bir entegrasyonun yan\u0131 s\u0131ra insan ve teknolojinin kombinasyonunu destekleyen geri bildirim i\u00e7in daha kapsaml\u0131 bir \u00e7er\u00e7eve benimsemekten de faydalanabilirler.<\/span><\/p>\n

                                  KAYNAK\u00c7A<\/h2>\n

                                  Abbas, S., & Sawamura, H. (2009). Developing an argument learning environment using agent-based ITS (ALES). In T. Barnes, M. Desmarais, C. Romero, & S. Ventura (Eds.), Proceedings of the 2nd International Conference on Educational Data Mining <\/i>(EDM2009), 1\u20133 July 2009, Cordoba, Spain (pp. 200\u2013209). International Educational Data Mining Society. <\/span><\/span><\/p>\n

                                  Allen, L. K., & McNamara, D. S. (2015). You are your words: Modeling students\u2019 vocabulary knowledge with natural language processing tools. In O. C. Santos et al. (Eds.), Proceedings of the 8th International Conference on Educational Data Mining <\/i>(EDM2015), 26\u201329 June 2015, Madrid, Spain (pp. 258\u2013265). International Educational Data Mining Society. <\/span><\/span><\/p>\n

                                  Arnold, K. E., Lonn, S., & Pistilli, M. D. (2014). An exercise in institutional reflection: The learning analytics readiness instrument (LARI). Proceedings of the 4th International Conference on Learning Analytics and Knowledge <\/i>(LAK\u201914), 24\u201328 March 2014, Indianapolis, IN, USA (pp. 163\u2013165). New York: ACM. doi:10.1145\/2567574.2567621 <\/span><\/span><\/p>\n

                                  Arroyo, I., Meheranian, H., & Woolf, B. P. (2010). Effort-based tutoring: An empirical approach to intelligent tutoring. In R. S. J. d. Baker, A. Merceron, & P. I. Pavlik Jr. (Eds.), Proceedings of the 3rd International Conference on Educational Data Mining <\/i>(EDM2010), 11\u201313 June 2010, Pittsburgh, PA, USA (pp. 1\u201310). International Educational Data Mining Society.<\/span><\/span><\/p>\n

                                  Baepler, P., & Murdoch, C. J. (2010). Academic analytics and data mining in higher education. International Journal for the Scholarship of Teaching and Learning, 4<\/i>(2). doi:10.20429\/ijsotl.2010.040217 <\/span><\/span><\/p>\n

                                  Baker, R., & Inventado, P. S. (2014). Educational data mining and learning analytics. In J. A. Larusson & B. White (Eds.), Learning analytics: From research to practice (pp. 61\u201375). Springer. <\/span><\/span><\/p>\n

                                  Baker, R., & Siemens, G. (2014). Educational data mining and learning analytics. In R. K. Sawyer (Ed.), The Cambridge handbook of the learning sciences<\/i>. Cambridge University Press. <\/span><\/span><\/p>\n

                                  Bakharia, A., Kitto, K., Pardo, A., Ga\u0161evi\u0107, D., & Dawson, S. (2016). Recipe for success: Lessons learnt from using xAPI within the connected learning analytics toolkit. Proceedings of the 6th International Conference on Learning Analytics and Knowledge <\/i>(LAK\u201916), 25\u201329 April 2016, Edinburgh, UK (pp. 378\u2013382). New York: ACM. <\/span><\/span><\/p>\n

                                  Barker-Plummer, D., Cox, R., & Dale, R. (2009). Dimensions of difficulty in translating natural language into first order logic. In T. Barnes, M. Desmarais, C. Romero, & S. Ventura (Eds.), Proceedings of the 2nd International Conference on Educational Data Mining <\/i>(EDM2009), 1\u20133 July 2009, Cordoba, Spain (pp. 220\u2013229). International Educational Data Mining Society. <\/span><\/span><\/p>\n

                                  Barker-Plummer, D., Cox, R., & Dale, R. (2011). Student translations of natural language into logic: The grade grinder corpus release 1.0. In M. Pechenizkiy, T. Calders, C. Conati, S. Ventura, C. Romero, & J. Stamper (Eds.), Proceedings of the 4th Annual Conference on Educational Data Mining <\/i>(EDM2011), 6\u20138 July 2011, Eindhoven, The Netherlands (pp. 51\u201360). International Educational Data Mining Society. <\/span><\/span><\/p>\n

                                  Beheshitha, S. S., Hatala, M., Ga\u0161evi\u0107, D., & Joksimovi\u0107, S. (2016). The role of achievement goal-orientations when studying effect of learning analytics visualisations. Proceedings of the 6th International Conference on Learning Analytics and Knowledge <\/i>(LAK\u201916), 25\u201329 April 2016, Edinburgh, UK (pp. 54\u201363). New York: ACM. <\/span><\/span><\/p>\n

                                  Ben-Naim, D., Bain, M., & Marcus, N. (2009). A user-driven and data-driven approach for supporting teachers in reflection and adaptation of adaptive tutorials. In T. Barnes, M. Desmarais, C. Romero, & S. Ventura (Eds.), Proceedings of the 2nd International Conference on Educational Data Mining <\/i>(EDM2009), 1\u20133 July 2009, Cordoba, Spain (pp. 21\u201330). International Educational Data Mining Society. <\/span><\/span><\/p>\n

                                  Black, P., & Wiliam, D. (1998). Assessment and classroom learning. Assessment in Education: Principles, Policy & Practice, 5<\/i>(1), 7\u201374. doi:10.1080\/0969595980050102 <\/span><\/span><\/p>\n

                                  Bouchet, F., Azevedo, R., Kinnebrew, J. S., & Biswas, G. (2012). Identifying students\u2019 characteristic learning behaviors in an intelligent tutoring system fostering self-regulated learning. In K. Yacef, O. Za\u00efane, A. Hershkovitz, M. Yudelson, & J. Stamper (Eds.), Proceedings of the 5th International Conference on Educational Data Mining <\/i>(EDM2012), 19\u201321 June, 2012, Chania, Greece (pp. 65\u201372). International Educational Data Mining Society. <\/span><\/span><\/p>\n

                                  Boud, D. (2000). Sustainable assessment: Rethinking assessment for the learning society. Studies in Continuing Education, 22<\/i>(2), 151\u2013167. doi:10.1080\/713695728 <\/span><\/span><\/p>\n

                                  Boud, D., & Molloy, E. (2013). Rethinking models of feedback for learning: The challenge of design. Assessment & Evaluation in Higher Education, 38<\/i>(6), 698\u2013712. doi:10.1080\/02602938.2012.691462 <\/span><\/span><\/p>\n

                                  Brusilovsky, P. (1996). Methods and techniques of adaptive hypermedia. User Modeling and User-Adapted Interaction, 6<\/i>, 87\u2013129. <\/span><\/span><\/p>\n

                                  Buckingham Shum, S., Sandor, A., Goldsmith, R., Wang, X., Bass, R., & McWilliams, M. (2016). Reflecting on reflective writing analytics: Assessment challenges and iterative evaluation of a prototype tool. Proceedings of the 6th International Conference on Learning Analytics and Knowledge <\/i>(LAK\u201916), 25\u201329 April 2016, Edinburgh, UK (pp. 213\u2013222). New York: ACM. <\/span><\/span><\/p>\n

                                  Bull, S., & Kay, J. (2016). SMILI : A framework for interfaces to learning data in open learner models, learning analytics and related fields. International Journal of Artificial Intelligence in Education, 26<\/i>(1), 293\u2013331. <\/span><\/span><\/p>\n

                                  Butler, D. L., & Winne, P. H. (1995). Feedback and self-regulated learning: A theoretical synthesis. Review of Educational Research, 65<\/i>(3), 245\u2013281. <\/span><\/span><\/p>\n

                                  Campbell, J. P., DeBlois, P. B., & Oblinger, D. (2007). Academic analytics: A new tool for a new era. EDUCAUSE Review, 42<\/i>, 40\u201357.<\/span><\/span><\/p>\n

                                  Charleer, S., Klerkx, J., & Duval, E. (2015). Exploring inquiry-based learning analytics through interactive surfaces. Proceedings of the Workshop on Visual Aspects of Learning Analytics <\/i>(VISLA\u201915), 16\u201320 March 2015, Poughkeepsie, NY, USA. http:\/\/ceur-ws.org\/Vol-1518\/paper6.pdf <\/span><\/span><\/p>\n

                                  Clow, D. (2012). The learning analytics cycle: Closing the loop effectively. Proceedings of the 2nd International Conference on Learning Analytics and Knowledge <\/i>(LAK\u201912), 29 April\u20132 May 2012, Vancouver, BC, Canada (pp. 134\u2013138). New York: ACM. doi:10.1145\/2330601.2330636 <\/span><\/span><\/p>\n

                                  Clow, D. (2014). Data wranglers: Human interpreters to help close the feedback loop. Proceedings of the 4th International Conference on Learning Analytics and Knowledge <\/i>(LAK\u201914), 24\u201328 March 2014, Indianapolis, IN, USA (pp. 49\u201353). New York: ACM. doi:10.1145\/2567574.2567603 <\/span><\/span><\/p>\n

                                  Corbett, A. T., Koedinger, K. R., & Anderson, J. R. (1997). Intelligent tutoring systems. In M. Heander, T. K. Landauer, & P. Prabhu (Eds.), Handbook of human\u2013computer interaction <\/i>(2nd ed., pp. 849\u2013870): Elsevier Science B. V. <\/span><\/span><\/p>\n

                                  Corrin, L., & de Barba, P. (2015). How do students interpret feedback delivered via dashboards? Proceedings of the 5th International Conference on Learning Analytics and Knowledge <\/i>(LAK\u201915), 16\u201320 March 2015, Poughkeepsie, NY, USA (pp. 430\u2013431). New York: ACM. doi:10.1145\/2723576.2723662 <\/span><\/span><\/p>\n

                                  Crossley, S., Allen, L. K., Snow, E. L., & McNamara, D. S. (2015). Pssst\u2026 textual features\u2026 there is more to automatic essay scoring than just you! Proceedings of the 5th International Conference on Learning Analytics and Knowledge <\/i>(LAK\u201915), 16\u201320 March 2015, Poughkeepsie, NY, USA (pp. 203\u2013207). New York: ACM. doi:10.1145\/2723576.2723595 <\/span><\/span><\/p>\n

                                  Crossley, S., Kyle, K., McNamara, D. S., & Allen, L. (2014). The importance of grammar and mechanics in writing assessment and instruction: Evidence from data mining. In J. Stamper, Z. Pardos, M. Mavrikis, & B. M. McLaren (Eds.), Proceedings of the 7th International Conference on Educational Data Mining <\/i>(EDM2014), 4\u20137 July, London, UK (pp. 300\u2013303). International Educational Data Mining Society. <\/span><\/span><\/p>\n

                                  Dawson, S. (2010). \u201cSeeing\u201d the learning community: An exploration of the development of a resource for monitoring online student networking. British Journal of Educational Technology, 41<\/i>(5), 736\u2013752. <\/span><\/span><\/p>\n

                                  Dawson, S., Bakharia, A., & Heathcote, E. (2010). SNAPP: Realising the affordances of real-time SNA within networked learning environments. In L. Dirckinck-Holmfeld, V. Hodgson, C. Jones, M. de Laat, D. McConnell, & T. Ryberg (Eds.), Proceedings of the 7th International Conference on Networked Learning <\/i>(NLC 2010), 3\u20134 May 2010, Aalborg, Denmark. http:\/\/www.networkedlearningconference.org.uk\/past\/nlc2010\/abstracts\/ PDFs \/ Dawson.pdf <\/span><\/span><\/p>\n

                                  De Liddo, A., Buckingham Shum, S., & Quinto, I. (2011). Discourse-centric learning analytics. Proceedings of the 1st International Conference on Learning Analytics and Knowledge <\/i>(LAK\u201911), 27 February\u20131 March 2011, Banff, AB, Canada (pp. 23\u201333). New York: ACM. <\/span><\/span><\/p>\n

                                  Deakin Crick, R., Huang, S., Ahmed Shafi, A., & Goldspink, C. (2015). Developing resilient agency in learning: The internal structure of learning power. British Journal of Educational Studies, 63<\/i>(2), 121\u2013160. doi: 10.1080 \/00071005.2015.1006574 <\/span><\/span><\/p>\n

                                  DeFalco, J. A., Baker, R., & D\u2019Mello, S. K. (2014). Addressing behavioral disengagement in online learning. Design recommendations for intelligent tutoring systems <\/i>(Vol. 2, pp. 49\u201356). Orlando, FL: U.S. Army Research Laboratory. <\/span><\/span><\/p>\n

                                  Dominguez, A. K., Yacef, K., & Curran, J. R. (2010). Data mining for generating hints in a python tutor. In R. S. J. d. Baker, A. Merceron, & P. I. Pavlik Jr. (Eds.), Proceedings of the 3rd International Conference on Educational Data Mining <\/i>(EDM2010), 11\u201313 June 2010, Pittsburgh, PA, USA (pp. 91\u2013100). International Educational Data Mining Society. <\/span><\/span><\/p>\n

                                  Eagle, M., & Barnes, T. (2013). Evaluation of automatically generated hint feedback. In S. K. D\u2019Mello, R. A. Calvo, & A. Olney (Eds.), Proceedings of the 6th International Conference on Educational Data Mining <\/i>(EDM2013), 6\u20139 July 2013, Memphis, TN, USA (pp. 372\u2013374). International Educational Data Mining Society\/Springer. <\/span><\/span><\/p>\n

                                  Eagle, M., & Barnes, T. (2014). Data-driven feedback beyond next-step hints. In J. Stamper, Z. Pardos, M. Mavrikis, & B. M. McLaren (Eds.), Proceedings of the 7th International Conference on Educational Data Mining <\/i>(EDM2014), 4\u20137 July, London, UK (pp. 444\u2013446). International Educational Data Mining Society.<\/span><\/span><\/p>\n

                                  Evans, C. (2013). Making sense of assessment feedback in higher education. Review of Educational Research, 83<\/i>(1), 70\u2013120. doi:10.3102\/0034654312474350 <\/span><\/span><\/p>\n

                                  Ezen-Can, A., & Boyer, K. E. (2013). Unsupervised classification of student dialogue acts with query-likelihood clustering. In S. K. D\u2019Mello, R. A. Calvo, & A. Olney (Eds.), Proceedings of the 6th International Conference on Educational Data Mining <\/i>(EDM2013), 6\u20139 July 2013, Memphis, TN, USA (pp. 20\u201327). International Educational Data Mining Society\/Springer. <\/span><\/span><\/p>\n

                                  Ezen-Can, A., & Boyer, K. E. (2015). Choosing to interact: Exploring the relationship between learner personality, attitudes, and tutorial dialogue participation. In O. C. Santos et al. (Eds.), Proceedings of the 8th International Conference on Educational Data Mining <\/i>(EDM2015), 26\u201329 June 2015, Madrid, Spain (pp. 125\u2013128). International Educational Data Mining Society. <\/span><\/span><\/p>\n

                                  Fancsali, S.E. (2014). Causal discovery with models: Behavior, affect, and learning in cognitive tutor algebra. In J. Stamper, Z. Pardos, M. Mavrikis, & B. M. McLaren (Eds.), Proceedings of the 7th International Conference on Educational Data Mining <\/i>(EDM2014), 4\u20137 July, London, UK (pp. 28\u201335). International Educational Data Mining Society. <\/span><\/span><\/p>\n

                                  Feng, M., Beck, J. E., & Heffernan, N. T. (2009). Using learning decomposition and bootstrapping with randomization to compare the impact of different educational interventions on learning. In T. Barnes, M. Desmarais, C. Romero, & S. Ventura (Eds.), Proceedings of the 2nd International Conference on Educational Data Mining <\/i>(EDM2009), 1\u20133 July 2009, Cordoba, Spain (pp. 51\u201360). International Educational Data Mining Society. <\/span><\/span><\/p>\n

                                  Ferguson, R., & Buckingham Shum, S. (2012). Social learning analytics: Five approaches. Proceedings of the 2nd International Conference on Learning Analytics and Knowledge <\/i>(LAK\u201912), 29 April\u20132 May 2012, Vancouver, BC, Canada (pp. 23\u201333). New York: ACM. <\/span><\/span><\/p>\n

                                  Gibson, A., & Kitto, K. (2015). Analysing reflective text for learning analytics: An approach using anomaly recontextualisation. Proceedings of the 5th International Conference on Learning Analytics and Knowledge <\/i>(LAK\u201915), 16\u201320 March 2015, Poughkeepsie, NY, USA (pp. 51\u201360). New York: ACM. doi:10.1145\/2723576.2723635 <\/span><\/span><\/p>\n

                                  Goldstein, P. J., & Katz, R. N. (2005). Academic analytics: The uses of management information and technology in higher education. Educause Center for Applied Research. <\/span><\/span><\/p>\n

                                  Graesser, A. C., Conley, M. W., & Olney, A. (2012). Intelligent tutoring systems. In K. R. Harris, S. Graham, & T. Urdan (Eds.), APA educational psychology handbook <\/i>(pp. 451\u2013473). American Psychological Association. <\/span><\/span><\/p>\n

                                  Grawemeyer, B., Mavrikis, M., Holmes, W., Guitierrez-Santos, S., Wiedmann, M., & Rummel, N. (2016). Affective off-task behaviour: How affect-aware feedback can improve student learning. Proceedings of the 6th International Conference on Learning Analytics and Knowledge <\/i>(LAK\u201916), 25\u201329 April 2016, Edinburgh, UK (pp. 104\u2013113). New York: ACM. <\/span><\/span><\/p>\n

                                  Hattie, J. (2008). Visible learning: A synthesis of over 800 meta-analyses related to achievement. New York: Routledge. <\/span><\/span><\/p>\n

                                  Hattie, J., & Timperley, H. (2007). The power of feedback. Review of Educational Research, 77<\/i>(1), 81\u2013112. doi:10.3102\/003465430298487 <\/span><\/span><\/p>\n

                                  Hegazi, M. O., & Abugroon, M. A. (2016). The state of the art on educational data mining in higher education. International Journal of Computer Trends and Technology, 31<\/i>, 46\u201356. <\/span><\/span><\/p>\n

                                  Howard, L., Johnson, J., & Neitzel, C. (2010). Examining learner control in a structured inquiry cycle using process mining. In R. S. J. d. Baker, A. Merceron, & P. I. Pavlik Jr. (Eds.), Proceedings of the 3rd International Conference on Educational Data Mining <\/i>(EDM2010), 11\u201313 June 2010, Pittsburgh, PA, USA (pp. 71\u201380). International Educational Data Mining Society. <\/span><\/span><\/p>\n

                                  Jeong, H., & Biswas, G. (2008). Mining student behavior models in learning-by-teaching environments. In R. S. J. d. Baker, T. Barnes, & J. E. Beck (Eds.), Proceedings of the 1st International Conference on Educational Data Mining <\/i>(EDM\u201908), 20\u201321 June 2008, Montreal, QC, Canada (pp. 127\u2013136). International Educational Data Mining Society. <\/span><\/span><\/p>\n

                                  Johnson, S., & Za\u00efane, O. R. (2012). Deciding on feedback polarity and timing. In K. Yacef, O. Za\u00efane, A. Hershkovitz, M. Yudelson, & J. Stamper (Eds.), Proceedings of the 5th International Conference on Educational Data Mining <\/i>(EDM2012), 19\u201321 June, 2012, Chania, Greece (pp. 220\u2013221). International Educational Data Mining Society. <\/span><\/span><\/p>\n

                                  Kickmeier-Rust, M., Steiner, C. M., & Dietrich, A. (2015). Uncovering learning processes using competence-based knowledge structuring and Hasse diagrams. Proceedings of the Workshop on Visual Aspects of Learning Analytics <\/i>(VISLA\u201915), 16\u201320 March 2015, Poughkeepsie, NY, USA (pp. 36\u201340). <\/span><\/span><\/p>\n

                                  Kinnebrew, J. S., & Biswas, G. (2012). Identifying learning behaviors by contextualizing differential sequence mining with action features and performance evolution. In K. Yacef, O. Za\u00efane, A. Hershkovitz, M. Yudelson, & J. Stamper (Eds.), Proceedings of the 5th International Conference on Educational Data Mining <\/i>(EDM2012), 19\u201321 June, 2012, Chania, Greece (pp. 57\u201364). International Educational Data Mining Society. <\/span><\/span><\/p>\n

                                  Kluger, A. N., & DeNisi, A. (1996). The effects of feedback interventions on performance: A historical review, a meta-analysis, and a preliminary feedback intervention theory. Psychological Bulletin, 119<\/i>(2), 254\u2013284. <\/span><\/span><\/p>\n

                                  Kobsa, A. (2007). Privacy-enhanced web personalization. In P. Brusilovsky, A. Kobsa, W. Nejdl (Eds.), The adaptive web: Methods and strategies of web personalization <\/i>(pp. 628\u2013670). Springer. doi:10.1007\/978-3-540- 72079-9_4. <\/span><\/span><\/p>\n

                                  Kulhavy, R. W., & Stock, W. A. (1989). Feedback in written instruction: The place of response certitude. Educational Psychology Review, 1<\/i>(4), 279\u2013308. <\/span><\/span><\/p>\n

                                  Lang, C., Heffernan, N., Ostrow, K., & Wang, Y. (2015). The impact of incorporating student confidence items into an intelligent tutor: A randomized controlled trial. In O. C. Santos et al. (Eds.), Proceedings of the 8th International Conference on Educational Data Mining <\/i>(EDM2015), 26\u201329 June 2015, Madrid, Spain (pp. 144\u2013149). International Educational Data Mining Society. <\/span><\/span><\/p>\n

                                  Lewkow, N., Zimmerman, N., Riedesel, M., & Essa, A. (2015). Learning analytics platform: Towards an open scalable streaming solution for education. In O. C. Santos et al. (Eds.), Proceedings of the 8th International Conference on Educational Data Mining <\/i>(EDM2015), 26\u201329 June 2015, Madrid, Spain (pp. 460\u2013463). International Educational Data Mining Society. <\/span><\/span><\/p>\n

                                  Lockyer, L., Heathcote, E., & Dawson, S. (2013). Informing pedagogical action: Aligning learning analytics with learning design. American Behavioral Scientist, 57<\/i>(10), 1439\u20131459. doi:10.1177\/0002764213479367 <\/span><\/span><\/p>\n

                                  Lonn, S., Aguilar, S., & Teasley, S. D. (2013). Issues, challenges, and lessons learned when scaling up a learning analytics intervention. Proceedings of the 3rd International Conference on Learning Analytics and Knowledge <\/i>(LAK\u201913), 8\u201312 April 2013, Leuven, Belgium (pp. 235\u2013239). New York: ACM. doi:10.1145\/2460296.2460343 <\/span><\/span><\/p>\n

                                  Lynch, C., Ashley, K. D., Aleven, V., & Pinkwart, N. (2008). Argument graph classification via genetic programming and C4.5. In R. S. J. d. Baker, T. Barnes, & J. E. Beck (Eds.), Proceedings of the 1st International Conference on Educational Data Mining <\/i>(EDM\u201908), 20\u201321 June 2008, Montreal, QC, Canada (pp. 137\u2013146). International Educational Data Mining Society. <\/span><\/span><\/p>\n

                                  Madhyastha, T. M., & Tanimoto, S. (2009). Student consistency and implications for feedback in online assessment systems. In T. Barnes, M. Desmarais, C. Romero, & S. Ventura (Eds.), Proceedings of the 2nd International Conference on Educational Data Mining <\/i>(EDM2009), 1\u20133 July 2009, Cordoba, Spain (pp. 81\u201390). International Educational Data Mining Society. <\/span><\/span><\/p>\n

                                  Mavrikis, M. (2008). Data-driven modelling of students\u2019 interactions in an ILE. In R. S. J. d. Baker, T. Barnes, & J. E. Beck (Eds.), Proceedings of the 1st International Conference on Educational Data Mining <\/i>(EDM\u201908), 20\u201321 June 2008, Montreal, QC, Canada (pp. 87\u201396). International Educational Data Mining Society. <\/span><\/span><\/p>\n

                                  McKay, T., Miller, K., & Tritz, J. (2012). What to do with actionable intelligence: E2Coach as an intervention engine. Proceedings of the 2nd International Conference on Learning Analytics and Knowledge <\/i>(LAK\u201912), 29 April\u20132 May 2012, Vancouver, BC, Canada (pp. 88\u201391). New York: ACM. doi:10.1145\/2330601.2330627 <\/span><\/span><\/p>\n

                                  Mendiburo, M., Sulcer, B., & Hasselbring, T. (2014). Interaction design for improved analytics. Proceedings of the 4th International Conference on Learning Analytics and Knowledge <\/i>(LAK\u201914), 24\u201328 March 2014, Indianapolis, IN, USA (pp. 78\u201382). New York: ACM. doi:10.1145\/2567574.2567628 <\/span><\/span><\/p>\n

                                  Mory, E. H. (2004). Feedback research revisited. In D. H. Jonassen (Ed.), Handbook of research on educational communication and technology <\/i>(Vol. 2, pp. 745\u2013783). Mahwah, NJ: Lawrence Erlbaum.<\/span><\/span><\/p>\n

                                  Nicol, D., & Macfarlane-Dick, D. (2006). Formative assessment and self-regulated learning: A model and seven principles of good feedback practice. Studies in Higher Education, 31<\/i>(2), 199\u2013218. doi:10.1080\/03075070600572090 <\/span><\/span><\/p>\n

                                  Olsen, J. K., Aleven, V., & Rummel, N. (2015). Predicting student performance in a collaborative learning environment. In O. C. Santos et al. (Eds.), Proceedings of the 8th International Conference on Educational Data Mining <\/i>(EDM2015), 26\u201329 June 2015, Madrid, Spain (pp. 211\u2013217). International Educational Data Mining Society. <\/span><\/span><\/p>\n

                                  Ostrow, K. S., & Heffernan, N. T. (2014). Testing the multimedia principle in the real world: A comparison of video vs. text feedback in authentic middle school math assignments. In J. Stamper, Z. Pardos, M. Mavrikis, & B. M. McLaren (Eds.), Proceedings of the 7th International Conference on Educational Data Mining <\/i>(EDM2014), 4\u20137 July, London, UK (pp. 296\u2013299). International Educational Data Mining Society. <\/span><\/span><\/p>\n

                                  Pardo, A., Ellis, R. A., & Calvo, R. A. (2015). Combining observational and experiential data to inform the redesign of learning activities. Proceedings of the 5th International Conference on Learning Analytics and Knowledge <\/i>(LAK\u201915), 16\u201320 March 2015, Poughkeepsie, NY, USA (pp. 305\u2013309). New York: ACM. doi:10.1145\/2723576.2723625 <\/span><\/span><\/p>\n

                                  Pardos, Z. A., Bergner, Y., Seaton, D. T., & Pritchard, D. E. (2013). Adapting Bayesian knowledge tracing to a massive open online course in edX. In S. K. D\u2019Mello, R. A. Calvo, & A. Olney (Eds.), Proceedings of the 6th International Conference on Educational Data Mining <\/i>(EDM2013), 6\u20139 July 2013, Memphis, TN, USA (pp. 137\u2013144). International Educational Data Mining Society\/Springer. <\/span><\/span><\/p>\n

                                  Pechenizkiy, M., Calders, T., Vasilyeva, E., & De Bra, P. (2008). Mining the student assessment data: Lessons drawn from a small scale case study. In R. S. J. d. Baker, T. Barnes, & J. E. Beck (Eds.), Proceedings of the 1st International Conference on Educational Data Mining <\/i>(EDM\u201908), 20\u201321 June 2008, Montreal, QC, Canada (pp. 187\u2013191). International Educational Data Mining Society. <\/span><\/span><\/p>\n

                                  Pechenizkiy, M., Trcka, N., Vasilyeva, E., van der Aalst, W., & De Bra, P. (2009). Process mining online assessment data. In T. Barnes, M. Desmarais, C. Romero, & S. Ventura (Eds.), Proceedings of the 2nd International Conference on Educational Data Mining <\/i>(EDM2009), 1\u20133 July 2009, Cordoba, Spain (pp. 279\u2013288). International Educational Data Mining Society. <\/span><\/span><\/p>\n

                                  Peddycord III, B., Hicks, A., & Barnes, T. (2014). Generating hints for programming problems using intermediate output. In J. Stamper, Z. Pardos, M. Mavrikis, & B. M. McLaren (Eds.), Proceedings of the 7th International Conference on Educational Data Mining <\/i>(EDM2014), 4\u20137 July, London, UK (pp. 92\u201398). International Educational Data Mining Society. <\/span><\/span><\/p>\n

                                  Piech, C., Huang, J., Chen, Z., Do, C., Ng, A., & Koller, D. (2013). Tuned models of peer assessment in MOOCs. In S. K. D\u2019Mello, R. A. Calvo, & A. Olney (Eds.), Proceedings of the 6th International Conference on Educational Data Mining <\/i>(EDM2013), 6\u20139 July 2013, Memphis, TN, USA (pp. 153\u2013160). International Educational Data Mining Society\/Springer. <\/span><\/span><\/p>\n

                                  Pinkwart, N. (2016). Another 25 years of AIED? Challenges and opportunities for intelligent educational technologies of the future. International Journal of Artificial Intelligence in Education, 26<\/i>(2), 771\u2013783. doi:10.1007\/s40593-016-0099-7 <\/span><\/span><\/p>\n

                                  Pintrich, P. R. (1999). The role of motivation in promoting and sustaining self-regulated learning. International Journal of Educational Research, 31<\/i>, 459\u2013470. doi:10.1016\/S0883-0355(99)00015-4 <\/span><\/span><\/p>\n

                                  Romero, C., & Ventura, S. (2013). Data mining in education. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 3<\/i>(1), 12\u201327. doi:10.1002\/widm.1075 <\/span><\/span><\/p>\n

                                  Ruiz, S., Charleer, S., Urretavizcaya, M., Klerkx, J., Fernandez-Castro, I., & Duval, E. (2016). Supporting learning by considering emotions: Tracking and visualisation. A case study. Proceedings of the 6th International Conference on Learning Analytics and Knowledge <\/i>(LAK\u201916), 25\u201329 April 2016, Edinburgh, UK (pp. 254\u2013263). New York: ACM. doi:10.1145\/2883851.2883888 <\/span><\/span><\/p>\n

                                  Shute, V. J. (2008). Focus on formative feedback. Review of Educational Research, 78<\/i>(1), 153\u2013189. doi:10.3102\/0034654307313795<\/span><\/span><\/p>\n

                                  Simsek, D., Shum, S. B., De Liddo, A., Ferguson, R., & S\u00e1ndor, \u00c1. (2014). Visual analytics of academic writing. Proceedings of the 4th International Conference on Learning Analytics and Knowledge <\/i>(LAK\u201914), 24\u201328 March 2014, Indianapolis, IN, USA (pp. 265\u2013266). New York: ACM. doi:10.1145\/2567574.2567577 <\/span><\/span><\/p>\n

                                  Snow, E. L., Allen, L. K., Jacovina, M. E., Perret, C. A., & McNamara, D. S. (2015). You\u2019ve got style: Detecting writing flexibility across time. Proceedings of the 5th International Conference on Learning Analytics and Knowledge <\/i>(LAK\u201915), 16\u201320 March 2015, Poughkeepsie, NY, USA (pp. 194\u2013202). New York: ACM. doi:10.1145\/2723576.2723592 <\/span><\/span><\/p>\n

                                  Stefanescu, D., Rus, V., & Graesser, A. C. (2014). Towards assessing students\u2019 prior knowledge from tutorial dialogues. In J. Stamper, Z. Pardos, M. Mavrikis, & B. M. McLaren (Eds.), Proceedings of the 7th International Conference on Educational Data Mining <\/i>(EDM2014), 4\u20137 July, London, UK (pp. 197\u2013201). International Educational Data Mining Society. <\/span><\/span><\/p>\n

                                  Suthers, D., & Verbert, K. (2013). Learning analytics as a \u201cmiddle space.\u201d Proceedings of the 3rd International Conference on Learning Analytics and Knowledge <\/i>(LAK\u201913), 8\u201312 April 2013, Leuven, Belgium (pp. 1\u20134). New York: ACM. doi:10.1145\/2460296.2460298 <\/span><\/span><\/p>\n

                                  Verbert, K., Duval, E., Klerkx, J., Govaerts, S., & Santos, J. L. (2013). Learning analytics dashboard applications. American Behavioral Scientist, 57<\/i>(10), 1500\u20131509. <\/span><\/span><\/p>\n

                                  Verbert, K., Govaerts, S., Duval, E., Santos, J. L., Assche, F., Parra, G., & Klerkx, J. (2014). Learning dashboards: An overview and future research opportunities. Personal and Ubiquitous Computing, 18<\/i>(6), 1499\u20131514. doi:10.1007\/s00779-013-0751-2 <\/span><\/span><\/p>\n

                                  Wen, M., Yang, D., & Ros\u00e9, C. P. (2014). Sentiment analysis in MOOC discussion forums: What does it tell us? In J. Stamper, Z. Pardos, M. Mavrikis, & B. M. McLaren (Eds.), Proceedings of the 7th International Conference on Educational Data Mining <\/i>(EDM2014), 4\u20137 July, London, UK (pp. 130\u2013137). International Educational Data Mining Society. <\/span><\/span><\/p>\n

                                  Whitelock, D., Twiner, A., Richardson, J. T. E., Field, D., & Pulman, S. (2015). OpenEssayist: A supply and demand learning analytics tool for drafting academic essays. Proceedings of the 5th International Conference on Learning Analytics and Knowledge <\/i>(LAK\u201915), 16\u201320 March 2015, Poughkeepsie, NY, USA (pp. 208\u2013212). New York: ACM. doi:10.1145\/2723576.2723599 <\/span><\/span><\/p>\n

                                  Wiliam, D., Lee, C., Harrison, C., & Black, P. (2004). Teachers developing assessment for learning: Impact on student achievement. Assessment in Education: Principles, Policy & Practice, 11<\/i>(1), 49\u201365. doi:10.1080\/0969594042000208994 <\/span><\/span><\/p>\n

                                  Winne, P. H. (2014). Issues in researching self-regulated learning as patterns of events. Metacognition and Learning, 9<\/i>(2), 229\u2013237. doi:10.1007\/s11409-014-9113-3 <\/span><\/span><\/p>\n

                                  Winne, P. H., & Baker, R. (2013). The potentials of educational data mining for researching metacognition, motivation and self-regulated learning. Journal of Educational Data Mining, 5<\/i>(1), 1\u20138. <\/span><\/span><\/p>\n

                                  Wise, A. F. (2014). Designing pedagogical interventions to support student use of learning analytics. Proceedings of the 4th International Conference on Learning Analytics and Knowledge <\/i>(LAK\u201914), 24\u201328 March 2014, Indianapolis, IN, USA (pp. 203\u2013211). New York: ACM. <\/span><\/span><\/p>\n

                                  Zimmerman, B.J. (1990). Self-regulated learning and academic achievement: An overview. Educational Psychologist, 25(<\/i>1), 3\u201317. doi:10.1207\/s15326985ep2501_2<\/span><\/span><\/p>\n

                                  \n
                                  \n

                                  1<\/a> orj. self\u2014 reflection<\/span><\/span><\/p>\n<\/div>\n

                                  \n

                                  2<\/a> orj. reflective writing<\/span><\/span><\/p>\n<\/div>\n","protected":false},"author":1,"menu_order":10,"template":"","meta":{"pb_show_title":"on","pb_short_title":"","pb_subtitle":"","pb_authors":[],"pb_section_license":""},"chapter-type":[48],"contributor":[],"license":[],"class_list":["post-72","chapter","type-chapter","status-publish","hentry","chapter-type-numberless"],"part":46,"_links":{"self":[{"href":"https:\/\/acikkitap.com.tr\/oaek\/wp-json\/pressbooks\/v2\/chapters\/72","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/acikkitap.com.tr\/oaek\/wp-json\/pressbooks\/v2\/chapters"}],"about":[{"href":"https:\/\/acikkitap.com.tr\/oaek\/wp-json\/wp\/v2\/types\/chapter"}],"author":[{"embeddable":true,"href":"https:\/\/acikkitap.com.tr\/oaek\/wp-json\/wp\/v2\/users\/1"}],"version-history":[{"count":0,"href":"https:\/\/acikkitap.com.tr\/oaek\/wp-json\/pressbooks\/v2\/chapters\/72\/revisions"}],"part":[{"href":"https:\/\/acikkitap.com.tr\/oaek\/wp-json\/pressbooks\/v2\/parts\/46"}],"metadata":[{"href":"https:\/\/acikkitap.com.tr\/oaek\/wp-json\/pressbooks\/v2\/chapters\/72\/metadata\/"}],"wp:attachment":[{"href":"https:\/\/acikkitap.com.tr\/oaek\/wp-json\/wp\/v2\/media?parent=72"}],"wp:term":[{"taxonomy":"chapter-type","embeddable":true,"href":"https:\/\/acikkitap.com.tr\/oaek\/wp-json\/pressbooks\/v2\/chapter-type?post=72"},{"taxonomy":"contributor","embeddable":true,"href":"https:\/\/acikkitap.com.tr\/oaek\/wp-json\/wp\/v2\/contributor?post=72"},{"taxonomy":"license","embeddable":true,"href":"https:\/\/acikkitap.com.tr\/oaek\/wp-json\/wp\/v2\/license?post=72"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}