Educational data mining studies in Turkey: a systematic review

Abstract

The purpose of this research is a comprehensive review of studies towards educational data mining (EDM) in Turkey. For the purpose of this study, graduate theses and articles conducted in Turkey were examined in detail. As a result of the literature review, 48 studies were analyzed in the context of the data mining purpose, the technique used in the study, the purpose of the study, the sample, the data sources and the analysis tool used in the study. In addition, the input variables used in the studies for estimating student achievement in EDM were examined. As a result of the research, it was found that EDM studies were mostly aimed at prediction from data mining tasks. One of the results of this study is that artificial neural networks are the most commonly used technique in EDM studies. When the distributions of EDM studies according to their objectives are examined, it is seen that studies are predominantly aimed at predicting student achievement. It is seen that university students are preferred as the sample in EDM studies, achievement scores are used as data source and SPSS application is used more as an analysis tool. In the last part of the research, recommendations were made based on the results to the researchers.