Çevrimiçi Öğrenme Ortamındaki Etkileşim Verilerine Göre Öğrencilerin Akademik Performanslarının Veri Madenciliği Yaklaşımı İle Modellenmesi
The purpose of this study is to model students' academic performance based on their interaction data in an online learning environment with the help of data mining techniques. As a part of the first research question, it was aimed to compare different classification algorithms in order to find the best algorithms and the best predictors of students' end of year academic performance. In another research question, it was investigated if it is possible or not to predict students' academic performance in previous weeks with the help of selected predictors and algorithm. The results of the study showed that 86% of students who failed and passed the course at the end of the year were classified correctly. When results related to early prediction of students' end of year academic performance are examined, it can be seen that by the third week, 74% of students can be accurately classified.