A Learning Analytics-Based Formative Assessment Framework for Supporting Students’ Self-Regulated Learning

Abstract

The use of learning analytics in formative assessment has the potential to help students monitor and manage their learning process more effectively, but its application in supporting self-regulated learning remains limited. This study aims to analyze the effectiveness of a learning analytics-based formative assessment framework in improving students' self-regulated learning. A quantitative approach with a one-group pretest-posttest quasi-experimental design was used, involving 60 students selected through purposive sampling. Data were collected through a self-regulated learning questionnaire and student activity data from the Learning Management System, then analyzed using descriptive statistics and a paired-sample t-test. The results showed improvements in students' ability to plan, monitor, and evaluate their learning, associated with substantial pre-to-post SRL gains (t = 18.42; p = 0.000); however, the absence of a control group limits causal inference. These findings suggest that learning analytics-based formative assessment can support independent learning and may serve as a learning evaluation strategy in higher education. The framework offers a practical basis for using LMS activity data in formative feedback in higher education.