Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/116151
PIRA download icon_1.1View/Download Full Text
Title: Non-academic learner socialisation with ChatGPT and its influences on learning English argumentative writing logic
Authors: Zhang, R
Zou, D 
Cheng, G
Issue Date: 2025
Source: Education and information technologies, Published: 27 October 2025, Online first articles, https://doi.org/10.1007/s10639-025-13776-2
Abstract: ChatGPT-assisted learning has been increasingly implemented and shown effectiveness at cognitive and affective levels. In this learning approach, learners may have non-academic socialisation with ChatGPT behaviourally by producing non-academic prompts and emotionally by developing a sense of relatedness with it, which, considering the reported benefit of non-academic learner socialisation, may contribute to the effectiveness of ChatGPT-assisted learning. So far, research on such non-academic socialisation and its impact remains limited. To fill in the gap and thereby enhance the understanding of ChatGPT-assisted learning, we explored the extent and nature of non-academic socialisation with ChatGPT among EFL learners and its effects on learning outcomes in English argumentative writing. We developed a GPT-4-powered bot for learning English argumentative writing logic and asked 40 EFL university students to use it for a 45-to-75-min period. We analysed their prompts and surveyed their senses of relatedness to measure their behavioural and emotional non-academic socialisation with ChatGPT. Pre-post tests, writing tasks, and questionnaire surveys were administered to assess their learning outcomes regarding logical knowledge, logical quality, and self-efficacy in English argumentative writing. Semi-structured interviews were also conducted. Findings indicate that EFL learners had upper-intermediate levels of non-academic socialisation with ChatGPT due to ChatGPT’s excellent capabilities of language understanding and generation, fostering social presence and homophily, and stimulating positive emotions among learners. The socialisation enhanced learning outcomes in English argumentative writing, especially logical knowledge, by improving feedback acceptance, motivating strategy application, and triggering a flow. Based on the findings, we recommend long-term ChatGPT-assisted learning of English argumentative writing logic with spontaneous non-academic socialisation and a distinct, engaging bot persona.
Keywords: Chatbot
ChatGPT
English argumentative writing
Logical learning
Social engagement
Publisher: Springer New York LLC
Journal: Education and information technologies 
ISSN: 1360-2357
EISSN: 1573-7608
DOI: 10.1007/s10639-025-13776-2
Rights: © The Author(s) 2025
Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
The following publication Zhang, R., Zou, D. & Cheng, G. Non-academic learner socialisation with ChatGPT and its influences on learning English argumentative writing logic. Educ Inf Technol (2025) is available at https://doi.org/10.1007/s10639-025-13776-2.
Appears in Collections:Journal/Magazine Article

Files in This Item:
File Description SizeFormat 
s10639-025-13776-2.pdf2.63 MBAdobe PDFView/Open
Open Access Information
Status open access
File Version Record of Version
Access
View full-text via PolyU eLinks SFX Query
Show full item record

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.