A Meta-analysis of ChatGPT’s Effects on English Writing in Korean Classrooms
4
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
This meta-analysis synthesizes evidence on the effects of ChatGPT-assisted instruction on English writing in Korean EFL contexts. A systematic search in RISS yielded 401 records; after screening under PRISMA procedures, 12 studies reporting writing outcomes were included and analyzed. Effect sizes were computed as Hedges’ g and pooled using random-effects models. The random-effects mean indicated a medium-to-large improvement in writing (g = 0.6867). Mixed-effects subgroup analyses detected no statistically significant differences by experimental design (pre-experimental vs. quasi-experimental), educational level (tertiary vs. secondary), or region (metropolitan vs. others). Meta-regression trends for duration (weeks, positive) and weekly intensity (sessions/week, negative) were suggestive but not statistically significant. Overall, ChatGPT-supported writing instruction yields meaningful gains and shows consistent effects at both secondary and tertiary levels; in practice, it is well suited to complement teacher feedback. Future studies should expand samples in secondary and non-metropolitan settings and employ stronger designs to clarify how duration and intensity shape outcomes.
Abstract
This meta-analysis synthesizes evidence on the effects of ChatGPT-assisted instruction on English writing in Korean EFL contexts. A systematic search in RISS yielded 401 records; after screening under PRISMA procedures, 12 studies reporting writing outcomes were included and analyzed. Effect sizes were computed as Hedges’ g and pooled using random-effects models. The random-effects mean indicated a medium-to-large improvement in writing (g = 0.6867). Mixed-effects subgroup analyses detected no statistically significant differences by experimental design (pre-experimental vs. quasi-experimental), educational level (tertiary vs. secondary), or region (metropolitan vs. others). Meta-regression trends for duration (weeks, positive) and weekly intensity (sessions/week, negative) were suggestive but not statistically significant. Overall, ChatGPT-supported writing instruction yields meaningful gains and shows consistent effects at both secondary and tertiary levels; in practice, it is well suited to complement teacher feedback. Future studies should expand samples in secondary and non-metropolitan settings and employ stronger designs to clarify how duration and intensity shape outcomes.