Despite growing interest in artificial intelligence in education, the effectiveness of AI-generated feedback in language learning remains unclear. This meta-analysis examined its impact on language learning performance and affective outcomes. A systematic search of the Web of Science and EBSCO databases (2004–2024), supplemented by manual journal searches, identified 55 eligible studies. Results indicated significant positive effects on learning performance (g = 1.106, p < 0.001; k = 49) and affective outcomes (g = 0.823, p < 0.001; k = 16). For performance outcomes, significant moderators included intervention duration, language skill, feedback source, delivery mode, target language, and language learning context. For affective outcomes, significant moderators included use of generative AI, language skill, delivery mode, target language, and language learning context. These findings advance understanding of the pedagogical value of AI-powered feedback and highlight instructional design and contextual factors shaping its impact. Limitations and future research directions are discussed.
No takes yet. Share an insight, caveat, or question.
Chen et al. (2026) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: