Abstract
This forum article revisits earlier claims about the relationship between corpus linguistics, data-driven learning (DDL), and generative AI three years after initial discussions of these issues. Drawing on recent developments in large language model (LLM) architectures, prompting strategies, and corpus-AI integration, the article reflects on how current research practices still need to evolve beyond traditional concordancing and basic AI-assisted analysis. It highlights emerging opportunities for combining generative AI with corpus resources in EAP and LSP contexts, while also emphasising the need for greater methodological clarity regarding prompting, data integration, and the interpretation of AI-generated language. The article concludes by arguing that the future of corpus-informed language research and pedagogy will likely lie in even closer integration between empirical corpus evidence and AI-mediated language technologies.
References
Baisa, V., & Suchomel, V. (2014). SkELL: Web interface for English language learning. In A. Horák & P. Rychlý (Eds.), Proceedings of the Eighth Workshop on Recent Advances in Slavonic Natural Language Processing (RASLAN 2014) (pp. 63–70). NLP Consulting. https://www.sketchengine.eu/wp-content/uploads/SkELL_2014.pdf
Charles, M. (2024). Benefits and Challenges of Using Do‐it‐yourself Corpora for Academic Writing Development. TESOL Quarterly, 58(3), 1205–1214. https://doi.org/10.1002/tesq.3276
Cheung, L., & Crosthwaite, P. (2025). CorpusChat: Integrating corpus linguistics and generative AI for academic writing development. Computer Assisted Language Learning. Advance online publication. https://doi.org/10.1080/09588221.2025.2506480
Crosthwaite, P., & Baisa, V. (2023). Generative AI and the end of corpus-assisted data-driven learning? Not so fast! Applied Corpus Linguistics, 3(3), Article 100066. https://doi.org/10.1016/j.acorp.2023.100066
Crosthwaite, P. and Baisa, V. (2024): Crosthwaite, P., & Baisa, V. (2024). A user-friendly corpus tool for disciplinary data-driven learning: Introducing CorpusMate. International Journal of Corpus Linguistics, 29(4), 595–610. https://doi.org/10.1075/ijcl.23056.cro
Crosthwaite, P., Sun, S. & Jiang, FK. (2026). If you do not like the results, change the prompt! Exploring issues with corpus-based analyses of human vs generative AI produced academic writing. The Modern Language Journal, to appear.
Crosthwaite, P., Smala, S., & Spinelli, F. (2025). Prompting for pedagogy? Australian F-10 teachers’ generative AI prompting use cases. The Australian Educational Researcher, 52, 1795–1825. https://doi.org/10.1007/s13384-024-00787-0
El-Farahaty, H. Integrating Corpora and AI Tools in the Teaching, Learning, and Assessing of Arabic/English Legal Translation. International Journal of Semiotics of Law 38, 2031–2060 (2025). https://doi.org/10.1007/s11196-025-10281-0
Hu, G. (2026). GenAI! GenAI? GenAI... Journal of English for Academic Purposes, 80, Article 101650. https://doi.org/10.1016/j.jeap.2026.101650
Jiang, F. (Kevin), & Hyland, K. (2025d). Rhetorical distinctions: Comparing metadiscourse in essays by ChatGPT and students. English for Specific Purposes, 79, 17–29. https://doi.org/10.1016/j.esp.2025.03.001
Kuteeva, M., & Andersson, M. (2025). Negotiating stance expressions in research writing with GenAI: A three-step prompt approach for ChatGPT. Research Methods in Applied Linguistics, 4(3), 100267.
Lusta, A., Demirel, Ö., & Mohammadzadeh, B. (2023). Language corpus and data driven learning (DDL) in language classrooms: A systematic review. Heliyon, 9(12), Article e22731. https://doi.org/10.1016/j.heliyon.2023.e22731
Mo, Z., & Crosthwaite, P. (2025). Exploring the affordances of generative AI large language models for stance and engagement in academic writing. Journal of English for Academic Purposes, 75, Article 101499. https://doi.org/10.1016/j.jeap.2025.101499
Römer, U., & O’Donnell, M. B. (2011). From student hard drive to web corpus (part 1): The design, compilation and genre classification of the Michigan Corpus of Upper-level Student Papers (MICUSP). Corpora, 6(2), 159–177. https://doi.org/10.3366/cor.2011.0011
Copyright (c) 2026 Peter Crosthwaite
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.