Using Learning Analytics to Explore the Role of Self-regulation in students’ Achievements in Synchronous Online Learning

Abstract

Learning analytics aims to understand and optimize learning process by collecting and analyzing traced learner’s data. To utilize its potential, it should involve educational theoretical frameworks to identify the indicators in the traced data as well as to interpret the results. In this paper, we use learning analytics to explore the role of students’ self-regulation in their achievements in synchronous online learning. The study identifies three indicators in students’ traced data to capture self-regulation: session attendance time, students’ submissions of self-assessments, and study regularity by assessing their correlations with the self-regulation scales measured by self-reported instruments. The results show that these indicators are positively correlated with the students’ achievements, so they can be used to predict students’ performance in synchronous online learning, and identify students at risk.