Cover not available

Article In: International Journal of Corpus Linguistics: Online-First Articles

Dissecting AI discourse

A multidimensional analysis of LLM-generated and human-written argumentative essays

ORCiD logo with link | Beihang University
This content is being prepared for publication; it may be subject to changes.
Abstract
This study investigates the discourse characteristics of AI-generated argumentative essays designed to simulate student writing, comparing them with human-authored texts to explore linguistic variation and its implications for academic discourse. While large language models (LLMs) such as ChatGPT demonstrate impressive fluency and coherence, questions remain about their capacity to engage in nuanced argumentation and the critical reasoning expected in academic contexts. Employing Biber, D. (1988). Variation across speech and writing. Cambridge University Press. Google Scholar logo with link to Google Scholar multidimensional (MD) analysis, this study examines systematic differences between LLM-generated and human-written essays across dimensions of register variation, informational density, syntactic complexity, and persuasion. The results reveal that ChatGPT essays are markedly more informationally dense, context-independent, and abstract, yet exhibit reduced interpersonal engagement and overt persuasion compared with student essays. The paper concludes by reflecting on broader pedagogical and ethical implications for the integration of AI tools into academic writing and corpus-based research.
Article outline
  • 1.Introduction
  • 2.ChatGPT, writing assistance and corpus-based analysis
  • 3.Multidimensional analysis
  • 4.Data and analysis
    • 4.1Data collection
    • 4.2Data analysis
  • 5.Results
    • 5.1Overview of the corpora
    • 5.2Dimension 1: Informational versus involved discourse
    • 5.3Dimension 2: Narrative vs. non-narrative concerns
    • 5.4Dimension 3: Context-independent vs. context-dependent discourse
    • 5.5Dimension 4: Overt expression of persuasion
    • 5.6Dimension 5: Abstract and non-abstract information
  • 6.Discussion
  • 7.Conclusion
  • Notes
  • References
References (44)
References
Ansarifar, A., Shahriari, H., Staples, S., & Ghazanfari, M. (2025). A multi-dimensional analysis of thesis abstracts: Variation across academic levels and L1 backgrounds. Journal of English for Academic Purposes, 73, 101465.
Berber Sardinha, T. (2024). AI-generated vs human-authored texts: A multidimensional comparison. Applied Corpus Linguistics, 4(1), 100083. Google Scholar logo with link to Google Scholar
Biber, D. (1988). Variation across speech and writing. Cambridge University Press. Google Scholar logo with link to Google Scholar
(1989). A typology of English texts. Linguistics, 27(1), 3–43. Google Scholar logo with link to Google Scholar
(1995). Dimensions of register variation: A cross-linguistic comparison. Cambridge University Press. Google Scholar logo with link to Google Scholar
(2009). Multidimensional approaches. In A. Lüdeling & M. Kytö (Eds.), Corpus linguistics: An international handbook (pp. 822–855). Walter de Gruyter. Google Scholar logo with link to Google Scholar
Byrd, A. (2023). Truth-telling: Critical inquiries on LLMs and the corpus texts that train them. Composition Studies, 51(1), 135–142. [URL]
Crosthwaite, P. (2016). A longitudinal multidimensional analysis of EAP writing: Determining EAP course effectiveness. Journal of English for Academic Purposes, 22, 166–178. Google Scholar logo with link to Google Scholar
Curry, N., McEnery, T., & Brookes, G. (2025). A question of alignment — AI, GenAI and applied linguistics. Annual Review of Applied Linguistics, 45, 315–336. Google Scholar logo with link to Google Scholar
Friginal, E., & Weigle, S. (2014). Exploring multiple profiles of L2 writing using multi-dimensional analysis. Journal of Second Language Writing, 26, 80–95. Google Scholar logo with link to Google Scholar
Gardner, S., Nesi, H., & Biber, D. (2018). Discipline, level, genre: Integrating situational perspectives in a new MD analysis of university student writing. Applied Linguistics, 40(4), 646–674. Google Scholar logo with link to Google Scholar
Granger, S. (1998). The computer learner corpus: A versatile new source of data for SLA research. In S. Granger (Ed.), Learner English on computer (pp. 3–18). Addison Wesley Longman. Google Scholar logo with link to Google Scholar
(2017). Academic phraseology: A key ingredient in successful L2 academic literacy. Oslo Studies in Language, 9(3), 9–27. Google Scholar logo with link to Google Scholar
Halliday, M. A. K. (1988). On the language of physical science. In M. Ghadessy (Ed.), Registers of written English: Situational factors and linguistic features (pp. 162–178). Pinter Publishers.Google Scholar logo with link to Google Scholar
Hamid, M. O., & Crosthwaite, P. (2024). Developmental corpus insights into the writing life of a primary school child in Australia. Australian Review of Applied Linguistics, 47(1), 27–50. Google Scholar logo with link to Google Scholar
Herbold, S., Hautli-Janisz, A., Heuer, U., Kikteva, Z., & Trautsch, A. (2023). A large-scale comparison of human-written versus ChatGPT-generated essays. Scientific Reports, 13(1), 18617. Google Scholar logo with link to Google Scholar
Hyland, K. (2022). Teaching and researching writing (4th ed.). Routledge. Google Scholar logo with link to Google Scholar
Hyland, K., & Jiang, F. K. (2019). Academic discourse and global publishing: Disciplinary persuasion in changing times. Routledge. Google Scholar logo with link to Google Scholar
Ingley, S. J., & Pack, A. (2023). Leveraging AI tools to develop the writer rather than the writing. Trends in Ecology & Evolution, 38(9), 785–787. Google Scholar logo with link to Google Scholar
Jiang, F. K., & Hyland, K. (2025a). Does ChatGPT argue like students? Bundles in argumentative essays. Applied Linguistics, 46(3), 375–391. Google Scholar logo with link to Google Scholar
(2025b). Does ChatGPT write like a student? Engagement markers in argumentative essays. Written Communication, 42(3), 463–492. Google Scholar logo with link to Google Scholar
(2025c). Metadiscursive nouns in academic argument: ChatGPT vs student practices. Journal of English for Academic Purposes, 75, 101514. Google Scholar logo with link to Google Scholar
(2025d). Rhetorical distinctions: Comparing metadiscourse in essays by ChatGPT and students. English for Specific Purposes, 79, 17–29. Google Scholar logo with link to Google Scholar
(2026). EAP in a changing world: Towards a new research agenda. Journal of English for Academic Purposes, 80, 101647. Google Scholar logo with link to Google Scholar
(in press). Taking a stance: AI generated versus student written argumentative essays. Applied Linguistics Review.
Jiang, F. K., & Su, H. (2026). Exemplification in ChatGPT and student argumentative writing: A local grammar analysis. Linguistics and Education, 93, 101533. Google Scholar logo with link to Google Scholar
Khalifa, M., & Albadawy, M. (2024). Using artificial intelligence in academic writing and research: An essential productivity tool. Computer Methods and Programs in Biomedicine Update, 5, 100145. Google Scholar logo with link to Google Scholar
Liu, J., & Xiao, L. (2022). A multi-dimensional analysis of conclusions in research articles: Variation across disciplines. English for Specific Purposes, 67, 46–61. Google Scholar logo with link to Google Scholar
Markey, B., Brown, D. W., Laudenbach, M., & Kohler, A. (2024). Dense and disconnected: Analyzing the sedimented style of ChatGPT-generated text at scale. Written Communication, 41(4), 571–600. Google Scholar logo with link to Google Scholar
Nguyen, L., & Barrot, J. S. (2024). Detecting and assessing AI-generated and human-produced texts: The case of second language writing teachers. Assessing Writing, 62, 100899. Google Scholar logo with link to Google Scholar
Nini, A. (2019). The Multi-Dimensional Analysis Tagger. In T. B. Sardinha & M. V. Pinto (Eds.), Multi-dimensional analysis: Research methods and current issues (pp. 67–94). Bloomsbury Academic. Google Scholar logo with link to Google Scholar
OpenAI. (2024, May 13). Hello GPT-4o: We’re announcing GPT-4o, our new flagship model that can reason across audio, vision, and text in real time. OpenAI. [URL]
Qiu, X., Lo, Y. Y., & Teng, X. S. (2022). Development of L2 disciplinary literacy: A multidimensional analysis. System, 110, 102907. Google Scholar logo with link to Google Scholar
Revell, T., Yeadon, W., Cahilly-Bretzin, G., Clarke, I., Manning, G., Jones, J., Mulley, C., Pascual, R. J., Bradley, N., Thomas, D., & Leneghan, F. (2024). Chatgpt versus human essayists: An exploration of the impact of artificial intelligence for authorship and academic integrity in the humanities. International Journal for Educational Integrity, 20(1), 18. Google Scholar logo with link to Google Scholar
Stevenson, R. (2010). Advanced grammar for academic writing. Lulu Press.Google Scholar logo with link to Google Scholar
Su, Y., Lin, Y., & Lai, C. (2023). Collaborating with ChatGPT in argumentative writing classrooms. Assessing Writing, 57, 100752. Google Scholar logo with link to Google Scholar
Thompson, P., & Hunston, S. (2020). Interdisciplinary research discourse: Corpus investigations into environment journals. Routledge. Google Scholar logo with link to Google Scholar
Vee, A., Laquintano, T., & Schnitzler, C. (Eds.) (2023). TextGenEd: Teaching with text generation technologies. WAC Clearing House. [URL].
Venkadesh, D. (2023). How “ChatGPT” seems to look behind: Working of ChatGPT. Kaggle. [URL]
Wolfram, S. (2023, February 14). What is ChatGPT doing… and why does it work? StephenWolfram.com. [URL].
Yu, X. (2022). A multi-dimensional analysis of English-medium massive open online courses (MOOCs) video lectures in China. Journal of English for Academic Purposes, 55, 101079. Google Scholar logo with link to Google Scholar
Mobile Menu Logo with link to supplementary files background Layer 1 jbe-platform.quadraat-sans-bold jbe-platform.quadraat-sans-bold-dark jbe-platform.quadraat-sans-bold-light jbe-platform.quadraat-sans-bold prag Twitter_Logo_Blue