A Study on AI-Assisted Feedback in ESL Writing: A Case Study of ChatGPT

Abstract

To explore the application value of artificial intelligence in language teaching, this study used 277 ESL compositions by Chinese learners as its corpus. It invited three senior English teachers and ChatGPT-4 to grade the same set of compositions and systematically compared the similarities and differences in their feedback. The study found that ChatGPT provided significantly more feedback than the teachers. Teachers’ feedback focused on grammatical and vocabulary errors, demonstrating the characteristic of "precise focus"; ChatGPT, by contrast, conducted comprehensive corrections, frequently replacing vocabulary and structures, thereby reflecting the feature of "comprehensive coverage." In terms of feedback focus, ChatGPT excelled at optimizing written language style and delivering comprehensive feedback, whereas teachers tended to employ strategies of indirect feedback and targeted local guidance. Regarding personalization, teachers offered positive encouragement tailored to students’ backgrounds, rendering their feedback highly personalized; ChatGPT’s feedback, in contrast, was standardized and lacked emotional care for learners. The study also identified limitations of ChatGPT: inaccurate or excessive corrections, coupled with weak detection of logical errors; feedback language often exceeding students’ proficiency level, with extensive reformulations increasing cognitive load (in contrast to teachers’ feedback, which aligns with the "i+1" principle); and inappropriate remarks or fabricated academic references, which undermine academic integrity, compromise research credibility, and obscure achievement attribution. Based on these findings, the study proposes optimization suggestions to provide useful insights for ESL writing teaching practice.