Mapping the Usage of Definite and Indefinite Articles in Student and ChatGPT Essays: A Stylometric-Cartographic Approach

Authors

  • Tlatso Nkhobo
  • Chaka Chaka

Keywords:

AntConc; ChatGPT-generated discursive essays; Deleuzian-Guattarian cartographic mapping; English definite and indefinite articles; student-written discursive essays; usage frequencies; stylometry

Abstract

This study set out to investigate, analyse, and compare the usage frequencies of two English articles, the definite article, the, and the indefinite article, a, in two discursive essay sets. One set was written by first-year, English second language, undergraduate students (SWDEs), while the other set was generated by ChatGPT (CGDEs). Both essay sets responded to the same essay topic at different times (2023 and 2024). Each set comprised 50 essays, with the SWEDE set consisting of 27,183 tokens, whereas the CGDE set had 25,010 tokens. SWDEs were selected using convenience sampling, and all the 50 CGDEs were generated individually. The study employed a Deleuzian-Guattarian cartographic mapping and stylometry as its theoretical framing. In addition, it utilised AntConc to analyse its data. Some of the findings of this study are as follows. Pertaining to SWDEs, the definite article, the, had more usage frequencies than the indefinite article, a. A similar pattern was observed concerning CGDEs. Across the two essay sets, SWDEs recorded more usage frequencies of these two articles than CGDEs, with the definite article, the, having the most occurrence frequencies than the indefinite article, a, in both sets. With reference to cartographic representations of these two articles in the two essay sets, the study observed that these two articles can have multiple and varying representations that foreground their unfixed, indeterminate, fluid, and impermanent nature. This particular ephemeral nature, results in the cartographic deterritorialisation of these two articles across the two essay sets. This view inherently perceives student writing as being in a state of flux and negates the orthodox framing of student writing as predictable, linear, and stable. The study ends with recommendations and caveats regarding the use of these two English articles by English L2 students and by LLMs such as ChatGPT.

https://doi.org/10.26803/ijlter.24.12.34

References

Ahmad, K, & Khan, A. Q. (2021). The underlying reasons for the difficulties in use of the English articles for EFL learners: An analysis based on the learners’ experiences. Eurasian Journal of Applied Linguistics, 7(1), 420-434. https://doi.org/ 10.32601/ejal.911479

Ahmadin, M. (2022). Social research methods: Qualitative and quantitative approaches. Jurnal Kajian Sosial dan Budaya: Tebar Science, 6(1), 104-113. https://ejournal.tebarscience.com/index.php/JKSB/article/view/103

Allan, G. (2020). Handbook for research students in the social sciences. Routledge.

Banat, M. (2024). Investigating the linguistic fingerprint of GPT-4o in Arabic-to-English translation using stylometry. Journal of Translation and Language Studies, 5(3), 65-83. https://doi.org/10.48185/jtls.v5i3.1343

Benitez-Castro, M. A. (2021). Shell-noun use in disciplinary student writing: A multifaceted analysis of problem and way in third-year undergraduate writing across three disciplines. English for Specific Purposes, 61, 132-149., https://doi.org/10.1016/j.esp.2020.10.004

Berriche, L., & Larabi-Marie-Sainte, S. (2024). Unveiling ChatGPT text using writing style. Heliyon, 10(e32976), 1-19. https://doi.org/10.1016/j.heliyon.2024.e32976nb

Braswick, L. (2025). Most common ChatGPT words to avoid in 2025. https://walterwrites.ai/most-common-chatgpt-words-to-avoid/

Canfield, J. S. (2021) (Re) imagining cartographic techniques in writing pedagogy. https://www.proquest.com/docview/2624665807?fromopenview=true&pq-origsite=gscholar&sourcetype=Dissertations%20&%20Theses

Caquard, S. (2013). Cartography I: Mapping narrative cartography. Progress in Human Geography, 37(1), 135-144. https://doi.org/10.1177/0309132511423796

Caquard, S., & Cartwright, W. (2014). Narrative cartography: From mapping stories to the narrative of maps and mapping. The Cartographic Journal, 51(2), 101-106. https://doi.org/10.1179/0008704114Z.000000000130

Casal, J. E., & Kessler, M. (2023). Can linguists distinguish between ChatGPT/AI and human writing?: A study of research ethics and academic publishing. Research Methods in Applied Linguistics, 2(3). https://doi.org/10.1016/j.rmal.2023.100068

Castro-Varela, A. (2023). When the map shakes up the territory. Researching teachers’ learning through a non-representational cartographic approach. International Journal of Qualitative Studies in Education, 36(6), 1191-1206. https://doi.org/10.1080/09518398.2021.19302490309132511423796

Chaka, C. (2023a). Detecting AI content in responses generated by ChatGPT, Youchat, and Chatsonic: The case of five AI content detection tools. Journal of Applied Learning & Teaching, 6(2), 94-104. https://doi.org/10.37074/jalt.2023.6.2.12

Chaka, C. (2023b). Generative AI chatbots – ChatGPT versus YouChat versus Chatsonic: Use cases of Selected Areas of Applied English language studies. International Journal of Learning, Teaching and Educational Research, 22(6), 1-19. https://doi.org/10.26803/ijlter.22.6.1

Chaka, C.: (2024a). Reviewing the Performance of ai detection tools in differentiating between AI-generated and human-written texts: A literature and integrative hybrid review. Journal of Applied Learning & Teaching, 7(1), 115-126, https://doi.org/10.37074/jalt.2024.7.1.14

Chaka, C. (2024b). Accuracy Pecking Order – How 30 AI detectors stack up in detecting generative artificial intelligence content in university English L1 and English L2 student essays. Journal of Applied Learning & Teaching, 7(1), 127-139. https://doi.org/10.37074/jalt.2024.7.1.33.

Chaka, C., & Nkhobo, T. (2023). Applying Deleuzian and Guattarian principle of asignifying rupture in students’ online rhizomatic engagement patterns. In M. S. Khine (Ed.,), Rhizome metaphor: legacy of Deleuze and Guattari in education and learning (pp. 53-70). Springer. https://doi.org/10.1007/978-981-19-9056-4_4

Chan, A. Y. W. (2022). Typology and contexts of article errors: Investigation into the use of English articles by Hong Kong Cantonese ESL learners. International Review of Applied Linguistics in Language Teaching, 60(2), 197-227. https://doi.org/10.1515/iral-2018-0268

Cooper, D., Donaldson, C., & Murrieta-Flores, P. (2016). Literary mapping in the digital age, digital research in the arts and humanities. Routledge.

Deleuze, G., & Guattari, F. (1987). A thousand plateau: Capitalism and schizophrenia (B. Massumi, Trans.). University of Minnesota Press.

Derkach, K., & Alexopoulou, T. (2024). Definite and indefinite article accuracy in learner English: A multifactorial analysis. Studies in Second Language Acquisition, 46(3), 710-740. https://doi.org/10.1017/S0272263123000463

Divjak, D., Romain, L., & Milin, P. (2023). From their point of view: the article category as a hierarchically structured referent tracking system. Linguistics, 61(4), 1027-1068. https://doi.org/10.1515/ling-2022-0186

Eisen, M., Ribeiro, A., Segarra, S., & Egan, G. (2017). Stylometric analysis of early modern period English plays. Digital Scholarship in the Humanities, 33(3), 500-528. https://doi.org/10.1093/llc/fqx059

Fairbairn, D., Gartner, G., & Peterson, M. P. (2021). Epistemological thoughts on the success of maps and the role of cartography. International Journal of Cartography, 7(3), 317-331. https://doi.org/10.1080/23729333.2021.1972909

FaqeAbdulla, B. I. (2024). Analysis of definite and indefinite article usage in students’ paragraphs. Koya University Journal of Humanities and Social Sciences, 7(1), 494-501. https://doi.org/10.14500/kujhss.v7n1y2024.pp494-501.

Fu, L.; Liu, L. (2024). What are the differences? A comparative study of generative artificial intelligence translation and human translation of scientific texts. Humanities and Social Sciences Communications, 11(1), 1-12. https://doi.org/10.1057/S41599-024-03726-7

Gómez-Adorno, H., Posadas-Duran, J-P., Ríos-Toledo, G., Sidorov, G., & Gerardo Sierra, G. (2018). Stylometry-based approach for detecting writing style changes in literary texts. Computación y Sistemas, 22(1), 47-53. https://doi.org/10.13053/CyS-22-1-2882.

Grønmo, S. (2023). Social research methods: qualitative, quantitative and mixed methods approaches. Sage.

Hanley, C. (2019). Thinking with Deleuze and Guattari: An Exploration of writing as assemblage. Educational Philosophy and Theory, 51(4), 413-423. https://doi.org/10.1080/00131857.2018.1472574

Hernández-Hernández, F. H., Gil, J. M. S., & Coscollola, M. D. (2018). Cartographies as spaces of inquiry to explore teachers’ nomadic learning trajectories. Digital Education Review, 33, 105-119. https://doi.org/10.1344/der.2018.33.105-119

Hewson, J. (1972). Article and noun in English. Mouton.

Johnson, R. B., & Christensen, L. B. (2024). Educational research: quantitative, qualitative, and mixed approaches. Sage.

Kandel, B. (2020). Qualitative versus quantitative research. Marsyangdi Journal, 1(1), 1-5. https://www.academia.edu/49300627/Qualitative_Versus_Quantitative_Research

Kovalev, B. V. (2024). From classics to digital philology: On the origin and growth of stylometry. Philologia Classica, 19(2), 347-360. https://doi.org/10.21638/spbu20.2024.211

Kumarage, T., & Liu, H. (2023). Neural authorship attribution: stylometric analysis on large language models. https://arxiv.org/pdf/2308.07305

Kumarage, T., Agrawal, G., Sheth, P., Moraffah, R., Chadha, A., Garland, J., & Liu, H. (2024). A survey of AI-generated text forensic systems: Detection, attribution, and characterization. https://arxiv.org/pdf/2403.01152

Leavy, P. (2022). Research design: Quantitative, qualitative, mixed methods, arts-based, and community-based participatory research approaches. Guilford.

Leong, A. P. (2023). Clause complexing in research-article abstracts: Comparing human- and AI-generated texts. Explorations in English Language and Linguistics, 11(2), 99-132, 2023. https://doi.org/10.2478/exell-2023-0008 101275.

Liu, D., Deng, Y., & Yu, D. (2023). The nonuse of the definite article the in referencing definite nouns in research writing: An empirical study using both corpus and survey data and its implications. Journal of English for Academic Purposes, 65(101275). https://doi.org/10.1016/j.jeap.2023.101275

Lozi?, E., & Štular, B. (2023). Fluent but not factual: A Comparative analysis of ChatGPT and other AI chatbots’ proficiency and originality in scientific writing for humanities. Future Internet, 5(336). https://doi.org/10.3390/fi15100336

Lund, B. D., Wang, T., Mannuru, N .R., Nie, B., Shimray, S., & Wang, Z. (2023). Chatgpt and a new academic reality: Artificial intelligence-written research papers and the ethics of the large language models in scholarly publishing. Journal of the Association for Information Science and Technology, 74(5), 570-581. https://doi.org/10.1002/asi.24750

Maisto, A. (2025). Collaborative storytelling and LLM: A linguistic analysis of automatically-generated role-playing game sessions. https://doi.org/10.48550/arXiv.2503.20623

Masood, A. (2025). The authenticity deficit: is AI diluting your voice. https://medium.com/@adnanmasood/the-authenticity-deficit-is-ai-diluting-your-voice-54bd53afe01b

Master, P. (1997). The English article system: Acquisition, function, and pedagogy. System, 25(2), 215-232. https://doi.org/10.1016/S0346-251X(97)00010-9

Master, P. (2002). Information structure and English article pedagogy. System, 30(3), 331-348. https://doi.org/10.1016/S0346-251X(02)00018-0

Miller, J. (2005). Most of esl students have trouble with the articles. International Education Journal, 5(5), 80-88. https://files.eric.ed.gov/fulltext/EJ903889.pdf

Mura, M. L. (2023). Cartographic practice and literary tourism. The case of the Italian literary parks. https://www.unistrapg.it/en/cartographic-practice-and-literary-tourism-the-case-of-the-italian-literary-parks

Mwita, K. M. (2022). Strengths and weaknesses of qualitative research in social science studies. International Journal of Research in Business and Social Science, 11(6), 618-625. https://doi.org/10.20525/ijrbs.v11i6.1920

Nègre, J. (2024). Writing with maps. In T. Rossetto & L. L. Presti (Eds.,), The Routledge handbook of cartographic humanities. Routledge. https://doi.org/10.4324/9781003327578

Nkhobo, T., & Chaka, C. (2021). Exploring instances of Deleuzian Rhizomatic patterns in students’ writing and in online student interactions. International Journal of Learning, Teaching and Educational Research, 20(10), 1-22, https://doi.org/10.26803/ijlter.20.10.1

Nkhobo, T.; Chaka, C. (2023a). Student-written versus ChatGPT-generated discursive essays: A comparative Coh-Metrix analysis of lexical diversity, syntactic complexity, and referential cohesion. International Journal of Education and Development using Information and Communication Technology, 19(3), 69-84. http://ijedict.dec.uwi.edu/include/getdoc.php?id=10118&article=3310&mode=pdf

Nkhobo, T.; Chaka, C. (2023b). Syntactic pattern density, connectives, text easability, and text readability indices in students’ written essays: A Coh-Metrix analysis. Research Papers in Language Teaching and Learning, 13(1), 121-136. https://rpltl.eap.gr/images/2024/RPLTL14_Issue1.pdf

Nobre, M. T., Amorim, A. K. A., & Frangella, S. (2020). Ethnography, cartography, ethnomapping: Dialogues and compositions in the field of research. Estudos de Psicologia, 24(1), 54-64. https://doi.org/10.22491/1678-4669.20190007

Padilla-Petry, P., Hernández-Hernández, F., & Sánchez-Valero, J. A. (2021). Using cartographies to map time and space in teacher learning in and outside school. International Journal of Qualitative Methods, 20. https://doi.org/10.1177/1609406921992906

Park, S. (2023). Corpus analysis of L2 English article usage patterns & pedagogical implications. Cogent Education, 10(1). https://doi.org/10.1080/2331186X.2023.2197662.

Peterle, G. (2018). Carto-fiction: narrativising maps through creative writing. Social & Cultural Geography, 20(8), 1070-1093. https://doi.org/10.1080/14649365.2018.1428820

Reiter, B. (2017). Theory and methodology of exploratory social science research. International Journal of Science and Research, 5( 4), 129-150.

Rousell, D. (2021). A map you can walk into: Immersive cartography and the speculative potentials of data. Qualitative Inquiry, 27(5), 580-597. https://doi.org/10.1177/1077800420935927

Santee, J. (2021). Cartographic composition across the curriculum: Promoting cartographic literacy using maps as multimodal texts. Prompt: A Journal of Academic Writing Assignments, 6(2). https://doi.org/10.31719/pjaw.v6i2.95

Santee, J. (2023). Cartographic literacy can support social change approaches in technical communication courses. Journal of Technical Writing and Communication, 53(1), 50-67. https://doi.org/10.1177/00472816221125187 (last check 2025-08-19).

Sinaga, T. F. (2025). A forensic linguistic investigation of mahira’s suicide note using stylometric analysis. Langkawi: Journal of the Association for Arabic and English, 1(1), 160-76. https://doi.org/10.31332/lkw.v11i1.11838

Sinclair, J .M. (1991). Corpus, concordance, collocation. Oxford University Press.

Sison, A. J. G., Daza, M. T., Gozalo-Brizuela, R., & Garrido-Merchán, E. C. (2024) ChatGPT: More than a “weapon of mass deception” ethical challenges and responses from the human-centered artificial intelligence (HCAI) perspective. International Journal of Human–Computer Interaction, 40(17), 4853-4872. https://doi.org/10.1080/10447318.2023.222593

Steere, E. (2024). Anatomy of an AI essay. https://www.insidehighered.com/opinion/career-advice/teaching/2024/07/02/ways-distinguish-ai-composed-essays-human-composed-ones

Superbenji. (2024). Spot AI: Or, unveiling the nuances of AI-generated writing in 2024. https://www.superbenji.ai/post/spot-ai-or-unveiling-the-nuances-of-ai-generated-writing-in-2024

Tiwari, V., Kiyawat, D., Jain, D., Mahor, U., & Yadav, A. (2023). Stylometric analysis of genre in Hindi literature. International Journal on Recent and Innovation Trends in Computing and Communication, 11(9), 2674-2680. https://doi.org/10.17762/ijritcc.v11i9.9341

Ulmer, J. B., & Koro-Ljungberg, M. (2015). Writing visually through (methodological) events and cartography. Qualitative Inquiry, 21(2), 138-152. https://doi.org/10.1177/1077800414542706 9341 (last check 2025-08-19).

Wyatt, J., & Gale, K. (2018). Writing to it: Creative engagements with writing practice in and with the not yet known in today’s academy. International Journal of Qualitative Studies in Education, 31(2), 119-129. https://doi.org/10.1080/09518398.2017.1349957

Y?ld?z, Ç. (2025). Five surprising facts about ai chatbots that can help you make better use of them. https://theconversation.com/five-surprising-facts-about-ai-chatbots-that-can-help-you-make-better-use-of-them-259603

Zaitsu W., & Jin M. (2023) Distinguishing ChatGPT(-3.5, -4)-generated and human-written papers through Japanese stylometric analysis. PLoS ONE, 18(8), e0288453. https://doi.org/10.1371/journal.pone.0288453

Zenkov, A.V. (2024). The numbers reveal the author: A stylometric comparison of German-language modernist texts. ?????????: ??????? ????????????, 11, 50-62. https://doi.org/10.7256/2454-0749.2024.11.72167

Zindela, N. (2023). Comparing measures of syntactic and lexical complexity in artificial intelligence and L2 human-generated argumentative essays. International Journal of Education and Development using Information and Communication Technology, 19(3)50-68. http://ijedict.dec.uwi.edu/include/getdoc.php?id=10117&article=3312&mode=pdf

Downloads

Published

2025-12-30

How to Cite

Nkhobo, T. ., & Chaka , C. . (2025). Mapping the Usage of Definite and Indefinite Articles in Student and ChatGPT Essays: A Stylometric-Cartographic Approach. International Journal of Learning, Teaching and Educational Research, 24(12), 809–830. Retrieved from https://ijlter.net/index.php/ijlter/article/view/2644