Proceedings of the International Conference on Challenges and Trends in Arts and Social Sciences (ICCTASS 2025)

Enhancing Undergraduate Essay Writing through AI-Assisted Instruction: Evidence from a Quasi-Experimental Study

Authors
Kaspia Sultana1, Mafruha Ferdous1, *, Shaheen Akter1
1American International University–Bangladesh, Dhaka, Bangladesh
*Corresponding author. Email: mafruha@aiub.edu
Corresponding Author
Mafruha Ferdous
Available Online 30 May 2026.
DOI
10.2991/978-2-38476-581-2_23How to use a DOI?
Keywords
Artificial Intelligence (AI); Quasi-Experimental Method; Language Learning Technology First Section
Abstract

As artificial intelligence (AI) has become more widely used in higher education, there are numerous potentials to utilize AI to enhance academic writing and language learning. Using a quasi-experimental mixed-method approach, this study sought to assess how AI-assisted instructional technology affected undergraduate students’ essay-writing skills. Eighty students from the Department of English at the American International University–Bangladesh, all enrolled in English writing courses, participated in an AI-assisted training module. Among them fifty-four students were placed in the experimental group and twenty-six in the control group. The experimental group received essay writing training using AI assistance, while the control group received traditional teaching. Grammar, vocabulary, topic sentence development, paragraph coherence, thesis statement formulation (limited to one complete sentence with a single full stop), and conclusion writing were all areas of focus for the intervention. A pre-test and post-test were administered to both groups, and essays were assessed based on predefined criteria that prioritized the quality of the thesis statement, paragraph development, coherence, grammar, and conclusion. Effectiveness and predictive validity were evaluated using statistical methods, such as regression, correlation and independent and paired t-tests. By giving students timely and targeted feedback on their grammar, vocabulary, organization, and academic expression, the results showed that AI-assisted training greatly enhanced students’ writing. In line with previous studies on AI-assisted language acquisition, the results offered empirical proof that academic writing performance can be improved by AI-assisted tools for both proficient and struggling learners.

Copyright
© 2026 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

Volume Title
Proceedings of the International Conference on Challenges and Trends in Arts and Social Sciences (ICCTASS 2025)
Series
Advances in Social Science, Education and Humanities Research
Publication Date
30 May 2026
ISBN
978-2-38476-581-2
ISSN
2352-5398
DOI
10.2991/978-2-38476-581-2_23How to use a DOI?
Copyright
© 2026 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

TY  - CONF
AU  - Kaspia Sultana
AU  - Mafruha Ferdous
AU  - Shaheen Akter
PY  - 2026
DA  - 2026/05/30
TI  - Enhancing Undergraduate Essay Writing through AI-Assisted Instruction: Evidence from a Quasi-Experimental Study
BT  - Proceedings of the International Conference on Challenges and Trends in Arts and Social Sciences (ICCTASS 2025)
PB  - Atlantis Press
SP  - 293
EP  - 306
SN  - 2352-5398
UR  - https://doi.org/10.2991/978-2-38476-581-2_23
DO  - 10.2991/978-2-38476-581-2_23
ID  - Sultana2026
ER  -