ChatGPT vs Human Writing: A Qualitative and Quantitative Study of IELTS Task 2 Authorship
Abstract
Artificial intelligence tools, such as ChatGPT, have recently become increasingly prevalent in the academic world due to their remarkable capabilities for generating essays, including logical structure, contextual relevance, and advanced vocabulary. Undoubtedly, these tools outperform humans in many aspects; however, despite their language-driven strengths, machine-generated content exhibits apparent shortcomings that make it easily identifiable as machine-authored. This article examines the critical deficiencies and limitations of AI writing, with a focus on the significant qualitative and quantitative differences between human-written and automated texts. It emphasises the originality and emotional colouring of human writing while highlighting the absence of these qualities in AI-generated essays despite their linguistic advantages. These findings may guide educators in helping learners refine their writing skills, identify common errors in human writing, and recognise the unique style that distinguishes it from machine-generated writing. The outcomes can be helpful not only in the academic environment but also in AI development, making the generated texts more closely resemble human writing.
Keywords
Full Text:
PDFReferences
1. Durak, H. Y., Eğin, F., & Onan, A. (2025). A comparison of Human‐Written versus AI‐Generated text in discussions at educational settings: investigating features for ChatGPT, Gemini and BingAI. European Journal of Education, 60(1). doi: 10.1111/ejed.70014
2. 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). doi: 10.1007/s40979-024-00161-8
3. Islam, N., Sutradhar, D., Noor, H., Raya, J. T., Maisha, M. T., & Farid, D., MD. (2023). Distinguishing human-generated text from ChatGPT-generated text using machine learning. arXiv (Cornell University). doi: 10.48550/arxiv.2306.01761
4. Weber-Wulff, D., Anohina-Naumeca, A., Bjelobaba, S., Foltýnek, T., Guerrero-Dib, J., Popoola, O., Šigut, P., & Waddington, L. (2023). Testing of detection tools for AI-generated text. International Journal for Educational Integrity, 19(1). doi: 10.1007/s40979-023-00146-z
5. Fariello, S., Fenza, G., Forte, F., Gallo, M., & Marotta, M. (2024). Distinguishing Human From Machine: A Review of Advances and Challenges in AI-Generated Text Detection. International Journal of Interactive Multimedia and Artificial Intelligence, In press, 1. doi: 10.9781/ijimai.2024.12.002
6. Alsaweed, W., & Aljebreen, S. (2024). Investigating the accuracy of ChatGPT as a writing error correction tool. International Journal of Computer-Assisted Language Learning and Teaching, 14(1), 1–18. doi: 10.4018/ijcallt.364847
7. Jahanzeb, J., Bisma, A., & Uzma, M. (2024). Enhancing Practical English Grammar Skills Through AI: A Study on the Impact of ChatGPT-Assisted Feedback on Student Writing. Contemporary Journal of Social Science Review, 2(4).
8. Barrot, J. S. (2023). Using ChatGPT for second language writing: Pitfalls and potentials. Assessing Writing, 57, 100745. doi: 10.1016/j.asw.2023.100745
9. Sardinha, T. B. (2023). AI-generated vs human-authored texts: A multidimensional comparison. Applied Corpus Linguistics, 4(1), 100083. doi: 10.1016/j.acorp.2023.100083
Article Metrics
Metrics powered by PLOS ALM
Refbacks
- There are currently no refbacks.
Copyright (c) 2025 Aida Akif Mirzayeva

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



