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
- Yan Li (ORCID: https://orcid.org/0000-0002-0640-1783)
- Azzeddine Boudouaia (ORCID: https://orcid.org/0000-0002-6919-7732)
- Jie Gao
Institutions
- University of Johannesburg (ZA)
- Southwest Jiaotong University (CN)
- Zhejiang University (CN)
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