Self-Regulated Learning Styles in Hybrid Learning Using Educational Data Mining Analysis

Abstract

Online learning requires a learning style consistent with learners’ behavior and performance. Therefore, this research has the significant goal of studying learning behaviors which accurate online learning management, with three main objectives: 1) to investigate the context of students’ self-regulated learning styles in hybrid learning situations, 2) to study clusters of learners formed by self-regulated learning styles in hybrid learning situations, and 3) to evaluate the appropriate cluster from self-regulated learning styles in hybrid learning situations. The data collected were 44 students from the School of Information and Communication Technology, University of Phayao, who received a hybrid learning approach during the 2022 academic year. The research tool applied machine learning principles, used unsupervised learning techniques to cluster learners’ appropriate learning behaviors, and elbow assessment techniques were used to determine the number of clusters appropriately consistent with the self-regulated learning styles. The results showed that learners who used the online learning approach had lower learning achievements than those who used the onsite learning approach in the course 221101[5] Fundamental Information Technology in Business. In addition, the study found a significant difference in the learning achievement of the two groups of students. Therefore, this research is a tool for designing learner groups consistent with learners’ behavior and potential in science and technology issues based on the self-regulated learning styles in hybrid learning situations.