PROMPTED BAND LABELS AND LINGUISTIC PATTERNING IN AI-GENERATED IELTS WRITING

Authors

  • Wirdatul Khasanah PSDKU Universitas Negeri Surabaya
  • Herlinda Nur Fauziya PSDKU Universitas Negeri Surabaya
  • Dwiki Dermawan PSDKU Universitas Negeri Surabaya
  • Mulat Sarira PSDKU Universitas Negeri Surabaya

DOI:

https://doi.org/10.31851/hze05z19

Keywords:

Generative Artificial Intelligence, IELTS Writing Task 2, Band-Level Prompting, Lexical Diversity, Discourse Organization

Abstract

This study examines the extent to which a generative AI model demonstrates consistency and patterned variation when responding to IELTS Writing Task 2 prompts differentiated by band-level instructions. Specifically, it investigates how Google Gemini adapts its written output when producing essays aligned with distinct proficiency targets. Using a controlled research design, the study analyses 24 AI-generated essays produced under two band conditions Band 6.0 and Band 7.5 while holding the task prompt and topic constant, with band instruction as the sole experimental variable. Lexical diversity was measured using the Measure of Textual Lexical Diversity (MTLD) and the Moving Average Type-Token Ratio (MATTR), and discourse organisation was examined through key argumentative markers. The findings reveal that Band 7.5 prompts consistently generate essays with higher lexical diversity and more cohesive discourse organisation than Band 6.0 prompts, despite comparable text lengths. These results suggest that generative AI encodes latent representations of writing proficiency that are activated by band-level cues and realised probabilistically rather than deterministically. By adopting a within-system, corpus-based approach rather than comparing human and AI texts, this study demonstrates that proficiency distinctions in AI-generated writing emerge through systematic yet non-fixed adaptations, with important implications for AI-assisted language assessment and instruction.

References

Al Hosni, J. (2025). Preserving Authorial voice in academic texts in the age of generative ai: A thematic literature review. Arab World English Journal, 16(3), 244–258. https://doi.org/10.24093/awej/vol16no3.14

Amin, M. Y. M. (2023). AI and Chat GPT in Language Teaching: Enhancing EFL Classroom Support and Transforming Assessment Techniques. International Journal of Higher Education Pedagogies, 4(4), 1–15. https://doi.org/10.33422/ijhep.v4i4.554

Amirjalili, F., Neysani, M., & Nikbakht, A. (2024). Exploring the boundaries of authorship: a comparative analysis of AI-generated text and human academic writing in English literature. Frontiers in Education, 9(March), 1–11. https://doi.org/10.3389/feduc.2024.1347421

Andriani, E. L. (2025). ELTR Journal, e-ISSN 2579-8235 ,. 9(2), 86–112.

Cappello, N., Rodriguez, D., Hernandez, E., & Canabate, D. (2025). Writing in movement : movement-based performing arts for developing physical education teachers ’ identity Escribir moviéndose : artes escénicas en movimiento para desarrollar la identidad de docentes de educación física Authors How to cite in APA Keyword. Retos: Nuevas Tendencias En Educación Física, Deporte y Recreación, 63, 829–845. https://doi.org/10.47197/retos.v63.111684

Devitska, A., & Horvat-Choblya, A. (2024). Linguistic domains: comparison of texts written by human and artificial intelligence. Věda a Perspektivy, 11(42). https://doi.org/10.52058/2695-1592-2024-11(42)-358-365

El Maamri, O. (2025). Towards the modelling of a writing process integrating generative ai to develop the argumentative skills of secondary school writers. XLinguae, 18(1), 133–143. https://doi.org/10.18355/XL.2025.18.01.10

Erviti, A. I. (2017). Discourse constructions in English: meaning, form and hierarchies: A study from the point of view of the Lexical Constructional Model. https://dialnet.unirioja.es/servlet/tesis?codigo=121205

Fattah, H. A., Vadivel, B., Shaban, A. A., & Shanmugam, K. (2023). Enhancing English language education: the impact of ai integration in the classroom. Journal of Humanities and Education Development, 5(6), 116–123. https://doi.org/10.22161/jhed.5.6.15

Fleckenstein, J., Meyer, J., Jansen, T., Keller, S. D., Köller, O., & Möller, J. (2024). Do teachers spot AI? Evaluating the detectability of AI-generated texts among student essays. Computers and Education: Artificial Intelligence, 6(January). https://doi.org/10.1016/j.caeai.2024.100209

Huang, H.-Y. C., Barrett, N. E., Tseng, Lo, M.-F., & Chiung-Jung. (2024). The Effectiveness of Shadowing Practice with Web-Based Apps: Towards Promoting the Comprehensibility and Lexical-Level Intelligibility of EFL Students’ Presentations. English Teaching and Learning, 48, 505–524. https://link.springer.com/article/10.1007/s42321-023-00145-w

Jaya, A., Hartono, R., Wahyuni, S., & Yulianto, H. J. (2025). Los efectos de la estrategia de aprendizaje basado en proyectos con actividad física en función del género sobre el rendimiento escolar y la confianza en sí mismos de los estudiantes. Retos: Nuevas Tendencias En Educación Física, Deporte y Recreación, 66, 349–360. https://doi.org/10.47197/retos.v66.110067

Jiang, F. (Kevin), & Hyland, K. (2025). Does ChatGPT Write Like a Student? Engagement Markers in Argumentative Essays. Written Communication, 42(3), 463–492. https://doi.org/10.1177/07410883251328311

Joshi, A., Dabre, R., Kanojia, D., Li, Z., Zhan, H., Haffari, G., & Dippold, D. (2024). Natural Language Processing for Dialects of a Language: A Survey. Computer Science, 1(1). http://arxiv.org/abs/2401.05632

Lin, Z. (2025). Techniques for supercharging academic writing with generative AI. Nature Biomedical Engineering, 1(9), 426–431. https://doi.org/10.1038/s41551-024-01185-8

Liu, L. (2025). Impact of AI gamification on EFL learning outcomes and nonlinear dynamic motivation: Comparing adaptive learning paths, conversational agents, and storytelling. Education and Information Technologies, 30, 11299–11338. https://doi.org/10.1007/s10639-024-13296-5

Markauskaite, L., Marrone, R., Poquet, O., Knight, S., Martinez-Maldonado, R., Howard, S., Tondeur, J., De Laat, M., Buckingham Shum, S., Gašević, D., & Siemens, G. (2022). Rethinking the entwinement between artificial intelligence and human learning: What capabilities do learners need for a world with AI? Computers and Education: Artificial Intelligence, 3(February). https://doi.org/10.1016/j.caeai.2022.100056

Mazari, N. (2025). Building Metacognitive Skills Using AI Tools to Help Higher Education Students Reflect on Their Learning Process Resumen Introduction. RHS-Revista Humanismo y Sociedad, 13(1), 1–20. https://doi.org/https://doi.org/10.22209/rhs.v13n1a04

Mei, P., Brewis, D. N., Nwaiwu, F., Sumanathilaka, D., Alva-Manchego, F., & Demaree-Cotton, J. (2025). If ChatGPT can do it, where is my creativity? generative AI boosts performance but diminishes experience in creative writing. Computers in Human Behavior: Artificial Humans, 4(December 2024), 100140. https://doi.org/10.1016/j.chbah.2025.100140

Mubarok, Y., Sudana, D., Yanti, D., Sugiyo, Aisyah, A. D., & Af’idah, A. N. (2024). Abusive Comments (Hate Speech) on Indonesian Social Media: A Forensic Linguistics Approach. Academic Journal, 14(5), 1440. https://doi.org/10.17507/tpls.1405.16

Pham, T. H. Van. (2022). Efl learners’ deployment of discourse markers in ielts essays: from beliefs to practices. Tạp Chí Nghiên Cứu Nước Ngoài. https://doi.org/10.25073/2525-2445/vnufs.4873

Putri, A. D., Jaya, A., & Marleni, M. (2023). Exploring the Students’ Speaking Ability Based on Their Different Personalities. Esteem Journal of English Education Study Programme, 6(1), 10–16. https://doi.org/10.31851/esteem.v6i1.10203

Révauger, G., & Rident, F. (2025). “I, too”, shall have to prompt? A study of EFL students and their unmonitored use of GenAI in the completion of an imitation task in poetry. Alsic, 1(28). https://doi.org/10.4000/137dy

Rodriguez-Donaire, S. (2024). Influence of Prompts Structure on the Perception and Enhancement of Learning through LLMs in Online Educational Contexts. https://doi.org/10.5772/intechopen.1006481

Rosdiana, S., Noercolies, M. A., & Fauzan, M. H. (2024). The Use of Artificial Intelligence in Teaching Writing Skills. EDUCASIA: Jurnal Pendidikan, Pengajaran, Dan Pembelajaran, 9(1), 45–56. https://doi.org/10.21462/educasia.v9i1.251

Saed, H. A., Haider, A. S., Al-Salman, S., & Hussein, R. F. (2021). The use of YouTube in developing the speaking skills of Jordanian EFL university students. Heliyon, 7(7), e07543. https://doi.org/10.1016/j.heliyon.2021.e07543

Sharma, A., Kumar, P., & Dhamija, S. (2025). From Prompts to Performance. 223–252. https://doi.org/10.1002/9781394287499.ch10

Sherine, A., Seshagiri, A. V. S., & Sastry, M. M. (2020). Impact of whatsapp interaction on improving L2 speaking skills. International Journal of Emerging Technologies in Learning, 15(3), 250–259. https://doi.org/10.3991/ijet.v15i03.11534

Sheng Cheng, X., Wu, P., & Liang, L. (2025). Detecting the knowledge structure of generative artificial intelligence research. Journal of Information Science. https://doi.org/10.1177/01655515251353188

Soughati, N., El Hadi, K., & Flyura, A. (2025). Technopedagogical Making Workshop and Writing/ Programming. XLinguae, 18(1), 153–169. https://doi.org/10.18355/XL.2025.18.01.12

Torky, S. A. E. F. I., & Ahmed, N. H. A. E. G. S. (2025). Promoting EFL students’ reading comprehension, grammatical competence, collocational competence and critical thinking disposition via data-driven pedagogical translation. Egyptian Journal of Educational Sciences, 5(1), 191–266. https://doi.org/10.21608/ejes.2025.446747

Wu, J. (2025). Comparing Linguistic Features between Human-written High-Scoring IELTS Essays and AI-Generated ones. Journal of Humanities and Social Sciences Studies, 7(8), 68–77. https://doi.org/10.32996/jhsss.2025.7.8.8

Xiaofan, W., & Annamalai, N. (2025). Investigating the use of AI tools in English language learning: A phenomenological approach. Contemporary Educational Technology, 17(2). https://doi.org/10.30935/cedtech/16188

Zhang, M., & Crosthwaite, P. (2025). More human than human? Differences in lexis and collocation within academic essays produced by ChatGPT-3.5 and human L2 writers. IRAL - International Review of Applied Linguistics in Language Teaching, 1–28. https://doi.org/10.1515/iral-2024-0196

Downloads

Published

2026-02-10