Exploring online students’ self-regulated learning with self-reported surveys and log files: a data mining approach

ABSTRACT

Many researchers who are interested in studying students’ online self-regulated learning (SRL) have heavily relied on self-reported surveys. Data mining is an alternative technique that can be used to discover students’ SRL patterns from large data logs saved on a course management system. The purpose of this study was to identify students’ online SRL patterns with the use of data mining techniques. We examined both self-reported self-regulation surveys and log files to predict online students’ achievements and found using log files was more powerful in predicting students’ achievements in an online course than self-reported survey data. Discussions to enhance teaching and learning practices with the use of data mining are provided.

KEYWORDS:

• Data mining
• online learning
• self-regulated learning
• self-reported surveys
• log files

Notes on contributors

Moon-Heum Cho is an Association Professor in Sungkyunkwan University in Seoul, Korea. His research interests include self-regulated learning, online learning, data mining, and role of learning technologies to enhance meaningful learning.

Jin Soung Yoo is an Associate Professor in Indiana University and Purdue University at Ft. Wayne in the United States. Her research interests include data science (data mining, machine learning and statistics), database systems and spatial computing.