The Effectiveness of AI-Supported Personalized Feedback on Students’ Learning Outcomes and Motivation: A Meta-Analysis
Wenxuan Wang, Yiting Wang, Jiahua Chen, X Wang, Hui Zhang, Guo Chunli, Yan Peng · Journal of Educational Computing Research · 2025
With the advent of artificial intelligence, feedback in educational settings has become increasingly personalized, contributing to positive pedagogical outcomes. However, to date, no meta-analysis has systematically examined the impact of AI-supported personalized feedback on students’ learning outcomes and motivation. This study addresses that gap by conducting a meta-analysis of 40 peer-reviewed studies involving 5,849 participants, evaluating the effectiveness of AI-supported personalized feedback in enhancing learning outcomes and learning motivation. Results from the R-package meta-analysis indicate that AI-supported personalized feedback has a moderate effect on learning outcomes ( g = 0.58) and has a strong effect on learning motivation ( g = 0.82). Furthermore, the study examined nine moderating variables and identified three significant moderators: learner level, experimental period and types of feedback. Finally, the study presents several pedagogical recommendations and directions for future research. Most notably, it introduces a Three-Dimensional Framework for AI-Supported Personalized Feedback, offering practical insights for educators and instructional designers.