A Study on Using ChatGPT to Help Students With Dyslexia Learn Chinese and English Writing
Purpose This study investigates the impact of large language models (LLMs), for example, ChatGPT, in inclusive education. Design/Approach/Methods We develop a ChatGPT-assisted writing system, namely CHATTING , to support students with dyslexia in learning to write. Then, we investigate the impact of CHATTING on students’ writing performance (vocabulary size) and their engagement in learning. The study involved 101 students who were divided into an experimental group (learn with CHATTING ) and a control group (learn in traditional classes). The effectiveness of CHATTING in assisting students’ learning is evaluated by measuring students’ learning engagement with open-ended interviews. Findings The results indicate that, with the assistance of CHATTING , students with dyslexia demonstrate positive improvement in behavioral, emotional engagement, and intrinsic motivation, but a minor improvement in cognitive engagement. The study also discusses several opportunities, challenges, and insights for utilizing ChatGPT-assisted learning to enhance students’ learning motivation and provide personalized support for students with dyslexia. Originality/Value This work contributes to inclusive education by developing and evaluating the effectiveness of CHATTING , a ChatGPT-assisted writing system specifically designed for students with dyslexia. The limitations of using generative models in supporting students’ learning in writing are also highlighted.
Authors
- Shenghui Song (ORCID: https://orcid.org/0000-0001-6316-8415)
- Kuen Fung Sin (ORCID: https://orcid.org/0000-0001-8923-1443)
- Lik‐Hang Lee (ORCID: https://orcid.org/0000-0003-1361-1612)
- Ka Yan Fung (ORCID: https://orcid.org/0000-0001-7751-0760)
- Huamin Qu (ORCID: https://orcid.org/0000-0002-3344-9694)
- Rick Tze Leung Lui
Institutions
- Hong Kong Polytechnic University (HK)
- Hong Kong University of Science and Technology (HK)
- Education University of Hong Kong (HK)
Publication Details
- Journal
- ECNU Review of Education
- Published
- 2025-08-10
- DOI
- https://doi.org/10.1177/20965311251358269
- Primary Topic
- Online Learning and Analytics
- Type
- article
- Field-Weighted Citation Impact
- 0.00