A Study on AI-Assisted Feedback in ESL Writing: A Case Study of ChatGPT
Bibliographic record
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.009 | 0.046 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.005 | 0.003 |
| Scholarly communication | 0.003 | 0.003 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".