A discourse analysis of cohesive devices in human and AI-produced personal statements

Authors

  • Haidir Algi Gaffar Faridha English Education, Faculty of Letters, Universitas Negeri Malang, East Java, Indonesia
  • Syifaa Khoirunnisaa English Literature, Faculty of Language and Arts, Universitas Negeri Surabaya, East Java, Indonesia
  • Nurlina Maharani English Education, Faculty of Education and Teacher Training (Tarbiyah), Universitas Islam Negeri Sumatera Utara, Indonesia
  • Lailatul Nurjanah English Education, Faculty of Letters, Universitas Negeri Malang, East Java, Indonesia

DOI:

https://doi.org/10.22219/englie.v7i1.41321

Keywords:

Discourse analysis, cohesive devices, personal statements, human-generated texts, AI-generated texts

Abstract

This research paper investigates the significant differences and similarities in cohesion devices between personal statements created by AI and those written by humans for Masters of TESOL applications. Using qualitative methods, this study applies Halliday and Hasan's Cohesion Model to analyse six personal statements: three created by AI and three created by humans. The focus is on reference, substitution, conjunction, and lexical cohesion. The findings revealed that the human-generated texts used richer and more varied cohesion devices, including personal and demonstrative references, substitutions, and diverse conjunctions, which enhanced readability and engagement. In contrast, while efficient and coherent, AI-generated texts often lack personal touch and variety, resulting in a more segmented narrative. In addition, AI-generated texts exhibited a higher level of text difficulty and could be detected by AI tools at a rate of 8.05%, compared to 0% for texts written by humans. This study highlights the need for balanced, cohesive elements in AI-generated texts to ensure authenticity and readability, emphasizing the importance of sophisticated detection tools to distinguish between human writing and AI writing. These insights contribute to the EAP understanding of human–AI collaboration in academic writing and inform writing pedagogy and curriculum design by highlighting ways to incorporate AI awareness and critical engagement into instructional practices.

Downloads

Download data is not yet available.

References

Abbas, M. S. (2024). ChatGPT in academic writing: A boon or a bane? Journal of Electronic & Information System, 6(2), 16–24. https://doi.org/10.30564/jeis.v6i2.8491

Alsaedi, N. (2024). ChatGPT and EFL/ESL writing: A systematic review of advantages and challenges. English Language Teaching, 17, 41-50. https://doi.org/10.5539/elt.v17n5p41

Anderson, N., Belavy, D. L., Perle, S. M., Hendricks, S., Hespanhol, L., Verhagen, E., & Memon, A. R. (2023). AI did not write this manuscript, or did it? Can we trick the AI text detector into generated texts? The potential future of ChatGPT and AI in Sports & Exercise Medicine manuscript generation. BMJ Open Sport and Exercise Medicine, 9(1), 1–4. https://doi.org/10.1136/bmjsem-2023-001568

Barrot, J. S. (2023). Using ChatGPT for second language writing: Pitfalls and potentials. Assessing Writing, 57, 100745. https://doi.org/10.1016/j.asw.2023.100745

Chiu, Y.-L. T. (2016). ‘Singing your tune’: Genre structure and writer identity in personal statements for doctoral applications. Journal of English for Academic Purposes, 21, 48–59. https://doi.org/10.1016/j.jeap.2015.11.001

Crossley, S. (2020). Linguistic features in writing quality and development: An overview. Journal of Writing Research, 11(3), 415–443. https://doi.org/10.17239/JOWR-2020.11.03.01

Halliday, M. A. K., & Hasan, R. (2014). Cohesion in English (1st ed.). Routledge. https://doi.org/10.4324/9781315836010.

Ismail, H. Y. S. (2023). Cohesion and coherence in essays generated by chatgpt: a comparative analysis to university students’ writing. CDELT Occasional Papers in the Development of English Education, 83(1), 143–165. https://doi.org/10.21608/opde.2023.325331

Istihari, I., Sofiah, V., & Abidin, Y. (2023). An analysis of cohesion and coherence in analytical exposition texts generated by AI chatbot auto-generative system. In Proceedings of AISELT (pp. 68–84). https://jurnal.untirta.ac.id/index.php/aiselt/article/view/22245

Iswara, R. W., & Saleh, M. (2017). FTA and politeness strategies in prospective students’ personal statements to apply for a Master’s program abroad. English Education Journal, 7, 160–167. https://api.semanticscholar.org/CorpusID:149371992

Johnstone, R. E., Neely, G., & Sizemore, D. C. (2023). Artificial intelligence software can generate residency application personal statements that program directors find acceptable and difficult to distinguish from applicant compositions. Journal of Clinical Anesthesia, 89, 111185. https://doi.org/10.1016/j.jclinane.2023.111185

Lam, C. B. (2020). Discourse and perceptual analysis of AI-synthesized texts on coherence and cohesion (Doctoral dissertation, The University of Hong Kong). HKU Theses Online. http://hub.hku.hk/bitstream/10722/294338/1/FullText.pdf

Lancaster, T. (2025). Generative AI for academic writing: Case studies beyond simple chatbot interactions. Journal of Academic Writing, 15(S1), 1–16. https://doi.org/10.18552/joaw.v15iS1.1067

Li, Y., & Deng, L. (2019). I am what I have written: A case study of identity construction in and through personal statement writing. Journal of English for Academic Purposes, 37, 70–87. https://doi.org/10.1016/j.jeap.2018.11.005

Liang, W., Yuksekgonul, M., Mao, Y., Wu, E., & Zou, J. (2023). GPT detectors are biased against non-native English writers. Patterns, 4(7), 100779. https://doi.org/10.1016/j.patter.2023.100779

Lum, Z. C., Guntupalli, L., Saiz, A. M., Leshikar, H., Le, H. V, Meehan, J. P., & Huish, E. G. (2024). Can artificial intelligence fool residency selection committees? analysis of personal statements by real applicants and generative ai, a randomized, single-blind multicenter study. JB & JS Open Access, 9(4), 1-6. https://doi.org/10.2106/JBJS.OA.24.00028

Mak, M. H. C., & Walasek, L. (2025). Artificial intelligence style, sentiment, and quality of undergraduate writing in the AI era: A cross-sectional and longitudinal analysis of 4,820 authentic empirical reports. Computers and Education: Artificial Intelligence, 9, 100507. https://doi.org/10.1016/j.caeai.2025.100507

Matthiessen, S.M., Wang, B., Ma, Y., & Mwinlaaru, I.N. Systemic Functional Insights on Language and Linguistics. (2022). Springer. https://doi.org/10.1007/978-981-16-8713-6

Mizumoto, A., Yasuda, S., & Tamura, Y. (2024). Identifying ChatGPT-generated texts in EFL students’ writing: Through comparative analysis of linguistic fingerprints. Applied Corpus Linguistics, 4(3), 100106. https://doi.org/10.1016/j.acorp.2024.100106

Ngongo, M., & Ndandara, A. (2024). Exploring the realization of cohesion as a resource of text texture on undergraduate students’ academic writing. English Review Journal of English Education, 12, 343–352. https://doi.org/10.25134/erjee.v12i1.9241

Özdemir, O., & Seçkin, H. (2025). Exploring foreign language anxiety in higher education: Multifaceted insights into causes, impacts, and coping strategies. Social Sciences & Humanities Open, 11, 101364. https://doi.org/10.1016/j.ssaho.2025.101364

Patel, K. A., Suriano, C. J., & Janis, J. E. (2025). The role of ChatGPT in personal statements for plastic surgery residency applications: Program directors’ perspective. Plastic and Reconstructive Surgery – Global Open, 13(4), e6698. https://doi.org/10.1097/GOX.0000000000006698

Rasool, U., Qian, J., & Aslam, M. Z. (2022). An investigation of foreign language writing anxiety and its reasons among pre-service EFL teachers in Pakistan. Frontiers in Psychology, 13, 947867. https://doi.org/10.3389/fpsyg.2022.947867

Raza, H., Sarwar, M. S., & Qasim, D. H. M. (2025). Cohesion in ESL argumentative essays: An SFL analysis of university students’ writing across Punjab. Pakistan Social Sciences Review, 9(1). https://doi.org/10.35484/pssr.2025(9-I)52

Rokhaniyah, H., Adila, W., & Yulianti, D. A. B. (2022). Cohesive devices used in argumentative essays by undergraduate EFL learners. Langkawi: Journal of The Association for Arabic and English, 8(1), 32-44. https://doi.org/10.31332/lkw.v0i0.3491

Song, C., & Song, Y. (2023). Enhancing academic writing skills and motivation: Assessing the efficacy of ChatGPT in AI-assisted language learning for EFL students. 14:1260843, 1–14. https://doi.org/10.3389/fpsyg.2023.1260843

Steele, E., Steratore, A., Dilcher, B. Z., & Bandi, K. (2025). Comparative analysis of artificial intelligence-generated and human-written personal statements in emergency medicine applications. Cureus, 17(7), e88818. https://doi.org/10.7759/cureus.88818

Tabari, M.A., & Johnson, M. D. (2023). Exploring new insights into the role of cohesive devices in written academic genres. Assessing Writing, 57, 100749. https://doi.org/10.1016/j.asw.2023.100749

Todd, R. (2023). Cohesion and coherence analyses of extended written schizophrenic discourse: An exploratory case study. REFLections, 30, 180–202. https://doi.org/10.61508/refl.v30i2.265574

Wittkower, D. E. (2020). What is it like to be a bot? The Oxford Handbook of Philosophy of Technology, 33, 358–373. https://doi.org/10.1093/oxfordhb/9780190851187.013.23

Yi, L. (2025). A cross-cultural investigation into the role of textual coherence in l2 writing quality. Journal of Linguistics and Communication Studies,4(1), 32-44. https://doi.org/10.56397/JLCS.2025.02.05

Downloads

Published

2026-02-04

How to Cite

Faridha, H. A. G., Khoirunnisaa, S., Maharani, N., & Nurjanah, L. (2026). A discourse analysis of cohesive devices in human and AI-produced personal statements. English Learning Innovation, 7(1), 124–141. https://doi.org/10.22219/englie.v7i1.41321

Issue

Vol. 7 No. 1 (2026): February

Section

Articles

License

Copyright (c) 2026 Faridha et al.

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Authors who publish with English Learning Innovation (englie)  agree to the following terms:

  1. For all articles published in English Learning Innovation (englie), copyright is retained by the authors. Authors give permission to the publisher to announce the work with conditions. When the manuscript is accepted for publication, the authors agree to automatic transfer of the publishing right to the publisher.
  2. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-ShareAlike 4.0 International License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
  3. Authors are able to 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 an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
  4. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their 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).

Creative Commons License” style=

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.