Download Full Text (937 KB)
Dr. Jin Soung Yoo
Department of Computer Science
Indiana University – Purdue University Fort Wayne
Educational data mining deals with developing methods for discovering uncovered information from educational context data. This study uses a dataset collected from online courses. The data record is composed of 45 attributes including: student’s year, gender, ethical background or weekly activities, and assessment values such as grade, intrinsic motivation, self-efficacy, effort regulation, metacognitive regulation, and interaction regulation. The goal of this study is to discover how self-motivation (intrinsic motivation and self-efficacy) and learning strategies (effort regulation, metacognitive regulation, and interaction regulation) are related with actual achievement behaviors which are represented by grade and score. Various data mining techniques such as association, classification, and clustering are applied to the dataset. Contrary to typical assumptions in Education Domain, our results show there is no particular evidence of correlations between self-reported motivation and grade and between learning strategies and grade. The research suggests that traditional measures such as exams, total time spent, weekly activities, familiarity with assignment instruction and discussion are more related to student’s actual achievement.
Computer Sciences | Education | Physical Sciences and Mathematics
Jeong, Hyonam, "Educational Data Mining: How Student’s Self-motivation and Learning Strategies Affect Actual Achievement" (2013). 2013 IPFW Student Research and Creative Endeavor Symposium. 27.