<![CDATA[Learning management systems generate detailed event logs, yet these data are often underused for monitoring student engagement. This study develops a learning analytics workflow for profiling engagement from Moodle activity logs collected from 20 courses. The raw dataset contained 402,290 records recorded between 19 February 2025 and 2 June 2025. After removing administrative, reporting, and system-maintenance events, 369,592 learner-generated events from 760 users were analyzed. The method consisted of timestamp parsing, course mapping, anonymization, event-category mapping, feature engineering, engagement scoring, and K-Means clustering. Eight behavioral indicators were constructed, including total events, active days, course views, module views, quiz activity, assignment activity, resource access, and event diversity. The results show that quiz-related interactions dominated the logs, followed by system course views and assignment activities. Three engagement profiles were identified: low, moderate, and high engagement. The proposed workflow provides an interpretable basis for course monitoring and early identification of learners who may require academic support, while avoiding unsupported claims about academic achievement when final-grade data are unavailable.]]>
Copyrights © 2026
