Beyond Language Gains: A Meta-Analysis of Non-Linguistic Outcomes of ChatGPT-Integrated English Instruction in South Korea

This meta-analysis investigates the outcomes associated with ChatGPT-integrated English instruction on non-linguistic outcomes in South Korea. Following the PRISMA 2020 guidelines, 22 experimental studies (k = 26, N = 1303) were synthesized using a random-effects model, which revealed a significant medium overall effect size (g = 0.55). Subgroup analyses showed medium-to-large effects in Affective (g = 0.67) and AI Literacy (g = 0.59) domains, but a small effect on Cognitive/Metacognitive outcomes (g = 0.17). Moderator analyses (e.g., educational level, duration) yielded no significant differences, suggesting a meaningful overall trend across contexts. However, the descriptive disparity between affective gains and cognitive growth indicates an ‘Affective–Cognitive Gap.’ Findings suggest that while ChatGPT is associated with a reduction in psychological barriers—partly by reducing mental effort—it may lead to ‘cognitive offloading’ without intentional pedagogical scaffolding. The study concludes that mere tool adoption is insufficient. To prevent a ‘plateau effect’ after the initial novelty wears off, instruction must evolve from passive use to ‘agentic engagement’ through structured metacognitive routines. These results emphasize the necessity of teacher-mediated integration to repurpose AI-afforded efficiency toward higher-order evaluative and critical thinking tasks.