The Effect of ChatGPT’s Grammar and Reformulation Feedback on EFL College Students’ Writing Performance

This study investigates the impact of ChatGPT’s grammar and reformulation feedback on the writing performance of EFL college students. Twenty-nine undergraduate EFL students from a Korea national university participated in this research, which utilizes ChatGPT-3.5 to provide automated grammar corrections and reformulation feedback, focusing on improvements in writing accuracy, fluency, and complexity. Using a pre-test and post-test design, the study also measures participants’ attitudes through a six-point Likert-scale questionnaire, analyzing their writing improvements based on IELTS descriptors. The results reveal statistically significant improvements in accuracy and fluency in student compositions. However, students noted minimal impact on complexity, suggesting that deeper noticing and engagement are necessary. This research highlights the potential of AI-driven feedback to support EFL learners and reduce instructor workload, while also emphasizing the importance of integrating awareness-raising activities by teachers or peers to maximize the utility of AI feedback.

Authors

Publication Details

Journal
Journal of AI Humanities
Published
2024-12-31
DOI
https://doi.org/10.46397/jaih.18.2
Citations
1
Primary Topic
Artificial Intelligence in Healthcare and Education
Type
article
Field-Weighted Citation Impact
0.12
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

The Effect of ChatGPT’s Grammar and Reformulation Feedback on EFL College Students’ Writing Performance

Shi Jing-xiu, Jaewoo Shim, Teresita Ryu
1 citations
Journal of AI Humanities
Artificial Intelligence in Healthcare and Education
0.12
article

The Effect of ChatGPT’s Grammar and Reformulation Feedback on EFL College Students’ Writing Performance

Shi Jing-xiu, Jaewoo Shim, Teresita Ryu
article en
1 citations

Abstract

This study investigates the impact of ChatGPT’s grammar and reformulation feedback on the writing performance of EFL college students. Twenty-nine undergraduate EFL students from a Korea national university participated in this research, which utilizes ChatGPT-3.5 to provide automated grammar corrections and reformulation feedback, focusing on improvements in writing accuracy, fluency, and complexity. Using a pre-test and post-test design, the study also measures participants’ attitudes through a six-point Likert-scale questionnaire, analyzing their writing improvements based on IELTS descriptors. The results reveal statistically significant improvements in accuracy and fluency in student compositions. However, students noted minimal impact on complexity, suggesting that deeper noticing and engagement are necessary. This research highlights the potential of AI-driven feedback to support EFL learners and reduce instructor workload, while also emphasizing the importance of integrating awareness-raising activities by teachers or peers to maximize the utility of AI feedback.

Journal of AI HumanitiesVol. 18
Quality Education
Openalex Percentile: Top 45%
Artificial Intelligence in Healthcare and Education
0.12
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

The Effect of ChatGPT’s Grammar and Reformulation Feedback on EFL College Students’ Writing Performance — Shi Jing-xiu, Jaewoo Shim, et al. · Journal of AI Humanities (2024) | TGRS Research Map | TGRS