A meta-analysis of AI-assisted self-regulated learning

This meta-analysis examines the effects of artificial intelligence (AI)-based pedagogical interventions on learners’ self-regulated learning and its subdomains, including cognitive, metacognitive, and resource management strategies. In addition, the study investigates whether these effects vary across four groups of moderators concerning research context, intervention design, AI, and self-regulated learning. A systematic search of databases identified an initial pool of 5,741 potentially relevant studies, of which 34 met all inclusion criteria. These studies yielded a total of 91 effect sizes. Results showed a positive overall effect of AI-based pedagogical interventions on self-regulated learning (Hedges’ g = 0.76). Positive effects were also observed across SRL subdomains (g = 0.48 for cognitive strategies, 0.73 for metacognitive strategies, and 0.93 for resource management strategies). Moderator analyses showed that the effects of AI-based interventions on self-regulated learning varied significantly across educational levels, AI pedagogical roles, and types of AI applications, whereas other factors such as discipline, intervention length, type of control group, sample size, SRL measure did not show significant differences. By synthesizing existing empirical evidence, this meta-analysis provides a quantitative foundation for understanding how and under what conditions AI can be effectively integrated into education to support learners’ self-regulated learning.