Answers are grounded in this paper and cite their sources.
This qualitative case study examined how ten secondary school ESL students in Malaysia used ChatGPT when revising their writing. The study did not focus on writing scores. Instead, it looked at students’ writing behaviours, the decisions they made when using ChatGPT, and the changes that appeared between their first and revised drafts. The students first wrote an essay on “Having a Balanced Diet” without using ChatGPT. After a short introduction to the tool, students revised the same essay with the help of ChatGPT. Data collection took place through writing samples from the students and semi-structured interviews. The interview data were analysed using thematic analysis, while the comparison between the first and the second drafts was conducted using document analysis. From the findings, it is clear that the students made use of ChatGPT to go through grammar, vocabulary, sentence structure, and content of their essays. Many improvements had been made in the revised drafts. Most of the students managed to fix grammar errors and use more suitable vocabulary, along with presenting new ideas in their work. Nonetheless, there are some flaws in the second drafts such as incorrect expressions, informal language and some incorrect ideas. The interviews also showed that the students did not accept the suggestions directly. The students chose those suggestions which were clear to them, appropriate to the task and related to their original meaning. Overall, the study shows that ChatGPT may be used to support ESL writing revision but students still need teacher guidance and their own judgement to use it critically and responsibly.
No takes yet. Share an insight, caveat, or question.
FREDELINA FRANKLIN FRANKEY (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: