Optimizing learning productivity: Personalized recommendations for habit-building through learning analytics

Abstract

This study investigates the development of productive learning habits through temporal regularity in learning activities. Building effective habits involves self-regulated learning (SRL) strategies, particularly in time management, which are critical for learners to regulate their behaviors and optimize their productivity. While Learning Analytics (LA) techniques have been employed to monitor habitual behaviors and provide long-term support, few of them attended to learners’ decisions on which habit to build when they try to find their optimal time for learning. To address this gap, we designed an algorithm that generates personalized recommendations for optimal learning time slots based on learning log data. Our findings reveal that these recommendations can increase learners’ awareness of productive time slots, guide them in aligning their behaviors with their goals, and support the development of sustainable learning habits. The study also highlights the implications for K-12 learners who often lack specific time management skills, and educators, who can leverage such tools to provide structured guidance and targeted feedback. By integrating adaptive learning systems and personalized recommendations, this study contributes to advancing SRL support within technology–enhanced learning environments, offering practical insights for improving time management, goal setting, and overall learning productivity.