Proposal of a Method for Analyzing Self-Regulated Learning Processes with Trace-Data of Learning Log from Digital Textbooks

Abstract

SRL (Self-Regulated Learning) is currently the subject of much research. In our previous studies, there are systems (STELLA) that can accumulate learners' learning history in digital textbooks and systems (SELFY) that support SRL by providing feedback to learners on their learning history collected by STELLA. However, since the evaluation method is in the form of a questionnaire, the evaluation is inherently subjective and often lacks real-time behavioral insight. Furthermore, existing methods are frequently domain-dependent, making it difficult to generalize findings across different subjects. Therefore, this study addresses two primary issues: (1) reliance on subjective evaluations through questionnaires and (2) the domain-dependence of existing SRL evaluation methods. Our purpose is to propose a trace-based, domain- independent analysis method that overcomes these limitations and enables more objective evaluation of SRL processes using digital textbook data. In this paper, we propose a method for analyzing SRL processes with trace-data of learning log from digital textbooks.