A Holistic Characterization of Self-Regulated Learning Based on Learning Process Mining Techniques (Poster 2)

• In Event: Thursday Poster Session 2:30 pm
  In Poster Session: Cognitive and Emotional Processes in Learning Environments

Abstract

It is of great significance to use learning process mining techniques (LPMT) to characterize self-regulated learning in college students. The present study analyzes 59 college students’ self-regulated learning behaviors by investigating their operational clickstream data within an online virtual simulation system. The heuristic mining algorithm was used to analyze the learning trajectory of groups with different self-regulated learning abilities. The results show that students in the high self-regulation group were more active in exploration and self-improvement, and their learning trajectories were significantly different from those in the medium and low ability groups. The results suggest that compared to a traditional coding-and-counting approach, the approach of LPMT provides more insight into the Self-Regulated Learning of students.

Authors

• Honghuan Lu, East China Normal University

• Jing Leng, East China Normal University