The Role of Generative Artificial Intelligence in IELTS Writing
DOI:
https://doi.org/10.22333/ijme.2025.10426Keywords:
generative artificial intelligence；syntactic complexity；IELTS writingAbstract
This study targeted intermediate-to-low-level learners of IELTS writing, employing generative AI technology as an intervention to systematically examine its influence on syntactic complexity. A mixed-methods approach was adopted, encompassing an 18-week teaching experiment with 50 participants. Theoretically, the research built upon Ortega et al.'s syntactic complexity framework and innovatively established a dual-track data collection system. This system combined automated assessment using natural language processing dependency parsing tools to extract T-unit structures with manual validation by two experienced IELTS instructors to ensure data reliability. Empirical analysis via paired-samples t-tests revealed statistically significant improvements in key metrics: the mean number of words per T-unit increased notably, and the clause ratio rose substantially (both p < 0.05), confirming AI's positive impact on syntactic complexity. Qualitative feedback from interviews and questionnaires highlighted that while AI excelled at providing real-time feedback, human teachers remained indispensable for fostering critical thinking, motivation, and emotional support. Based on these findings, the study proposed an "AI-Empowered, Teacher-Led" collaborative writing instruction model. This model integrates AI-driven adaptive feedback for syntactic development with teacher-guided activities focusing on argumentation and creativity. The research offers empirical evidence and practical insights for language teaching innovation in the intelligent education era, advocating blended learning that leverages the strengths of both AI and human instructors.
References
Banerjee J. Franceschina F.& Smith A, M. (2007). Documenting features of written language production typical at different IELTS band score levels. IELTS Research Reports Volume, 7, 1-56
Bao, G. (2009). A study on the changes of syntactic complexity in English learners' compositions. Foreign Language Teaching and Research, 4, 291-297.
British Council. (2024). IELTS test taker performance data report: Mainland China [EB/OL]. https://www.chinaielts.org/press-office/whitepaper-2024
Chen, M., & Lü, M. C. (2024). College English writing teaching in the ChatGPT environment. Contemporary Foreign Language Studies, 1, 161-168.
Hunt KW. (1965). Grammatical structures written at three grade levels. Champaign: The National Council of Teachers of English.
Jiao, J. L., & Chen, T. (2023). Large language models empowering English teaching: Four scenarios. Computer-Assisted Foreign Language Education, 2, 12-17.
Krashen S. D. (1985). The input hypothesis: Issues and implications. London: Longman Group Limited.
Ortega L. (2003). Syntactic complexity measures and their relationship to L2 proficiency: a research synthesis of college-level L2 writing. Applied Linguistics, 24, 492-518.
Qin, L. L., Dong, J. J., & Zhang, A. N. (2025). A study on English learners' emotional experiences in narrative writing revision mediated by generative AI: A Q-method research on continuation writing teaching. Foreign Languages in China, 2, 61-70.
Qiu, Y., Liu, J. X., Jiang, M., & Ding, Q. F. (2023). AI questioning made easy. Posts & Telecom Press.
UNESCO. (2023). Guidance for generative AI in education and research [EB/OL]. Retrieved from https://unesdoc.unesco.org/ark:/48223/pf0000386693
Wang, H. X. (2024). An exploration of the application of generative AI in college English teaching reform: Taking the teaching reform practice of "General Academic English Writing" as an example. Foreign Language Education Research in China, 4, 41-50, 95.
Wang, Y. B., Xuan, Q. Y., & Zhang, J. L. (2025). The impact of generative AI intervention on college students' engagement with feedback in foreign language writing. Foreign Languages in China, 2, 71-78.
Wen, Q. F., & Liu, R. Q. (2006). An analysis of college students' abstract thinking characteristics through English argumentative essays. Journal of Foreign Languages, 2, 49-58.
Xu, L. L., Hu, J. H., & Su, Y. (2024). A study on learners' cognition and behaviors in AI-assisted academic English writing. Foreign Language World, 3, 51-58.
Yang, L. X., & Ping, J. P. (2024). Generative AI and academic discourse writing from the perspective of metadiscourse. Contemporary Rhetoric, 6, 11-23.
Zhang Z ＆ Hyland K. (2018). Student engagement with teacher and automated feedback on L2 writing. Assessing Writing, 36, 90-102．
Zhao, Q., & Wang, S. Y. (2020). A study on the syntactic complexity of English compositions by students of different proficiency levels. Foreign Language Testing and Teaching, 3, 21-28.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Copyright (c) - Authors who publish with this journal agree to the following terms: Authors retain copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution-Noncommercial 4.0 International License, which allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their personal website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (see The Effect of Open Access). Authors may enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to a repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
