Meta-Analysis of the Impact of Artificial Intelligence-Based Teaching Feedback on Learning Outcomes

Abstract

This study is grounded in the practice of educational digital transformation, and was designed in strict accordance with the methodological norms of meta-analysis. By systematically sorting out the inconsistent research conclusions on artificial intelligence teaching feedback, we systematically searched and screened the China National Knowledge Infrastructure (CNKI) and Wanfang Database, and formulated strict literature inclusion and exclusion criteria, we ultimately selected 32 eligible empirical studies published in China from 2016 to 2024, involving a total effective sample of 12,486 participants. The random-effects model was adopted to calculate the pooled effect size, and we simultaneously conducted heterogeneity tests, publication bias assessments, and multidimensional moderating effect analyses. The results revealed that artificial intelligence teaching feedback had a pooled effect size of Hedges' g=0.51 (95% CI [0.42, 0.60], Z=11.24, p<0.001) on learning outcomes, representing a significant moderate positive facilitative effect; Academic stage, feedback type, and subject category all exerted significant moderating effects on the effect size. The research conclusions are consistent with the actual situation of classroom teaching, and the analytical process is rigorous and credible. This study thus provides robust empirical evidence for the implementation and application of artificial intelligence teaching feedback, its program optimization, and the construction of a localized precision teaching feedback system.