The Impact of AI-based Feedback on English Writing Performance: A Systematic Review and a Meta-analysis Study

Abstract

Artificial intelligence has increasingly transformed educational practices, particularly in writing instruction. Among these innovations, AI-based feedback tools have appeared as favourable solutions for giving personalized, immediate, and accessible support to learners. This study aims to assess the effect of AI-based feedback on English writing performance, filling research gaps regarding the impact of English language proficiency level, duration of intervention, and implementation setting on the effectiveness of AI-based feedback tools in improving students’ English language writing performance. A systematic review and meta-analysis were utilized to examine 24 empirical studies published from January 2022 to March 2026 across five databases (including EBSCO, ProQuest, ERIC, Web of Science, and Wiley Online Library). The results indicated that AI-based feedback tools had a large overall effect size (Hedges' g = 1.298, p < 0.001) on students’ writing performance. Moreover, moderator analyses revealed that learners with intermediate proficiency benefited more substantially compared to advanced learners, suggesting that AI feedback is particularly effective for developing writers. In terms of implementation settings, blended learning environments yielded stronger effects than traditional classroom settings, highlighting the importance of flexible and technology-supported contexts. Although the duration of intervention did not significantly moderate the results, consistently strong effects were observed across the three periods of intervention: short, medium, and long-term. These findings suggest that AI-based feedback tools represent a powerful and scalable approach to enhancing English writing skills.