Features and Strategies of Adaptive Learning Analytics Dashboards for Supporting Self-Regulated Learning

Abstract

This systematic review investigates the features and strategies of adaptive learning analytics dashboards (LADs) that support self-regulated learning (SRL), mapping them to its metacognitive, motivational, and behavioural components. This mapping is intended to strengthen students’ SRL skills. Using the Kitchenham method (2004), the study systematically analyzes 69 articles published from January 2019 to October 2024 through the planning, conducting, and reporting stages. Of these articles, 25 concern conventional LADs and 44 concern adaptive LADs implemented to support SRL. The findings indicate that the adaptive characteristics of LADs help students decide what action to take after analyzing their learning data. Recommended adaptive LAD features include goal-setting, progress tracking, self-assessment, feedback mechanisms, and performance prediction. These features promote monitoring and reflection, which may improve student motivation and active engagement. Future research should analyze adaptive LAD features that support SRL components in greater depth and use longitudinal designs to examine the effects of adaptive LADs on students’ SRL abilities.