Artificial intelligence feedback in EFL writing: evidence from ChatGPT, Pigai, and Bearly

Many students learning English as a foreign language (EFL) struggle with writing, and researchers have recommended combining ChatGPT with other programs to exploit their complementary strengths. Using a single-group pre-test–post-test design, this study investigated the valid-feedback coverage of ChatGPT, Pigai, and Bearly feedback and the combined use of the three tools in relation to students’ lower-level writing quality and revision process, drawing on 72 postgraduate students from the College of Philosophy at Zhejiang University. SPSS 27 was used for data analysis. ChatGPT and Pigai showed similar valid-feedback coverage for higher-level and lower-level writing subcategories, whereas Bearly’s coverage was higher for higher-level than lower-level subcategories. Students’ lower-level writing quality declined significantly from pre-test to post-test. When revising with the combined feedback, students focused most on sentence structure, word choice, grammar, and ideas and elaboration, frequently using “Change” and “Add” actions. Furthermore, revisions to ideas and elaboration, capitalization, word choice, grammar, and organization were most often successful. This study offers preliminary insights into the potential of artificial intelligence (AI) in EFL writing and identifies directions for future research.

Authors

Institutions

Publication Details

Journal
Humanities and Social Sciences Communications
Published
2026-11-21
DOI
https://doi.org/10.1057/s41599-026-09677-5
Primary Topic
EFL/ESL Teaching and Learning
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Artificial intelligence feedback in EFL writing: evidence from ChatGPT, Pigai, and Bearly

Yan Li, Azzeddine Boudouaia, Jie Gao
Humanities and Social Sciences Communications
EFL/ESL Teaching and Learning
article

Artificial intelligence feedback in EFL writing: evidence from ChatGPT, Pigai, and Bearly

Yan Li, Azzeddine Boudouaia, Jie Gao
article en

Abstract

Many students learning English as a foreign language (EFL) struggle with writing, and researchers have recommended combining ChatGPT with other programs to exploit their complementary strengths. Using a single-group pre-test–post-test design, this study investigated the valid-feedback coverage of ChatGPT, Pigai, and Bearly feedback and the combined use of the three tools in relation to students’ lower-level writing quality and revision process, drawing on 72 postgraduate students from the College of Philosophy at Zhejiang University. SPSS 27 was used for data analysis. ChatGPT and Pigai showed similar valid-feedback coverage for higher-level and lower-level writing subcategories, whereas Bearly’s coverage was higher for higher-level than lower-level subcategories. Students’ lower-level writing quality declined significantly from pre-test to post-test. When revising with the combined feedback, students focused most on sentence structure, word choice, grammar, and ideas and elaboration, frequently using “Change” and “Add” actions. Furthermore, revisions to ideas and elaboration, capitalization, word choice, grammar, and organization were most often successful. This study offers preliminary insights into the potential of artificial intelligence (AI) in EFL writing and identifies directions for future research.

Humanities and Social Sciences Communications
University of Johannesburg (ZA), Southwest Jiaotong University (CN), Zhejiang University (CN)
EFL/ESL Teaching and Learning
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.

Laika access coming soon