AI Chatbot as a Revision Aid in Second Language Writing: From Error Correction to Lexical Sophistication.
Background: The use of recent artificial intelligence (AI) chatbots, such as chat generative pretrained transformer (ChatGPT), in second language (L2) writing may face criticism for potentially promoting plagiarism and raising ethical concerns. However, such tools can effectively provide guided sugg...
| Published in: | Journal of Computer Assisted Learning Vol. 42; no. 3; pp. 1 - 21 |
|---|---|
| Main Authors: | , |
| Format: | pictorial research tables/charts Journal Article |
| Published: |
Wiley-Blackwell
Jun2026
|
| Online Access: | View this record in EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=194050903&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 194050903 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 02664909 6M1 jtl: Journal of Computer Assisted Learning issn: 02664909 maglogo: Y pubinfo: dt: Jun2026 vid: 42 iid: 3 pid: 480 pub: Wiley-Blackwell place: Malden, Massachusetts artinfo: ui: 194050903 194050903 194050903 10.1002/jcal.70259 194050903 ppf: 1 ppct: 20 formats: tig: atl: AI Chatbot as a Revision Aid in Second Language Writing: From Error Correction to Lexical Sophistication. aug: au: Chon, Yuah V. Shin, Dongkwang affil: Department of English Education, Hanyang University, Seoul, South Korea sug: subj: Chatbot Computer-Assisted Instruction Writing Evaluation English as a Second Language Education Linguistics Human Quasi-Experimental Studies Language Processing Students, College Comparative Studies Descriptive Statistics Teachers South Korea Analysis of Variance Paired T-Tests Post Hoc Analysis Pearson's Correlation Coefficient Scales Data Analysis Software Funding Source ab: Background: The use of recent artificial intelligence (AI) chatbots, such as chat generative pretrained transformer (ChatGPT), in second language (L2) writing may face criticism for potentially promoting plagiarism and raising ethical concerns. However, such tools can effectively provide guided suggestions for improving outlines, content, and organisation. Additionally, EditGPT, an extension that tracks changes made by ChatGPT, provides immediate, direct corrective feedback, thereby enhancing L2 learners' control over their writing process. Objectives: The aim of this study was to compare the quality of L2 learners' writing (LW), ChatGPT‐proofread writing (PW), and learners' ChatGPT‐supported revisions (RW) by analysing human raters' evaluations, assessing linguistic complexity, and identifying error types. Methods: A total of 40 university students majoring in English education, all of whom were English as a foreign language (EFL) learners and pre‐service teachers, participated in this study. Based on significant differences in their TOEIC scores, they were divided into two groups. The secondary‐school pre‐service teachers were classified as skilled learners, while the elementary‐school pre‐service teachers were identified as less skilled learners. Participants completed a guided writing task supported by ChatGPT for idea generation and essay revision. They interacted directly with ChatGPT using standard prompts for brainstorming and outlining and received automated feedback on editing and proofreading through the EditGPT extension. Results: When LW and RW were compared, human raters found significant improvements in language use but not in content and organisation. The revisions demonstrated greater linguistic complexity, including increased use of academic words, improved lexical sophistication, and more varied sentence structures. Regarding language errors, 86.17% of the errors in LW were successfully rectified. However, a closer breakdown revealed that certain error types—particularly word choice (38.9% remaining) and sentence structure (35.4% remaining)—remained relatively unresolved. Addressing these lingering errors in both PW and RW often required judgements of contextual appropriateness, especially when attempting to preserve the learners' intended meanings and nuanced expressions. As a result, the overall error resolution rate dropped to 77.02% in RW. Conclusions: The structured AI‐mediated revision environment was associated with short‐term improvements in the linguistic quality of L2 writing within a controlled session. These effects reflect product‐level changes and cannot be attributed to individual writing process components. While AI‐supported revision reduced many surface‐level errors, limitations remained for context‐sensitive language use. Further longitudinal research is needed to determine whether these changes support sustained writing development. Lay Description: What is Already Known About This Topic: Automated writing evaluation (AWE) tools help improve grammar and mechanics but have limitations in handling higher‐order writing skills.ChatGPT can offer grammar correction, vocabulary suggestions, and structural improvements in L2 writing.Concerns exist around ethical implications, academic integrity, and over‐reliance on AI‐generated content in educational settings. What This Paper Adds: Empirical evidence that ChatGPT, especially with EditGPT, significantly enhances linguistic accuracy and complexity in L2 writing.Demonstrates that ChatGPT‐supported revisions improve vocabulary use and syntactic sophistication, particularly among less skilled learners.Reveals persistent challenges with context‐sensitive language issues like word choice and sentence structure.Emphasises the importance of learner agency in evaluating and accepting AI‐generated feedback, rather than relying on passive adoption. Implications for Practice/or Policy: Teachers should provide guidance to help learners critically assess AI feedback to avoid misuse or over‐reliance.AI tools should be used as a supplement to—not a replacement for—human instruction, especially in developing higher‐order writing skills.Instructional designs should promote metacognitive strategies and reflective practices when integrating AI into writing pedagogy.Institutional policies should consider structured AI use in classrooms to maximise benefits while mitigating ethical and pedagogical risks. pubtype: Academic Journal doctype: pictorial research tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|