The Impact of ChatGPT on English Language Learners' Writing Skills: An Assessment of AI Feedback on Mobile
Open accessAbstract
Artificial intelligence (AI) has shown promise in enhancing English as a second language (ESL) writing skills by providing personalized feedback and targeted corrections, thereby facilitating improved grammar and composition proficiency. Despite the potential of AI tools like ChatGPT, their impact on common writing errors in ESL contexts has yet to be explored. This study employed a quasi-experimental design to compare the efficacy of ChatGPT’s mobile application feedback against traditional teacher feedback in a senior secondary public school in India. Over eight weeks, the experimental group received feedback on their writing error corrections through the ChatGPT application, while the control group received feedback from teachers. Additionally, participants’ attitudes towards using ChatGPT for language learning were assessed through a questionnaire administered post-intervention to 132 students. Data was collected using pre- and post-tests that involved writing stories based on pictures. The study results demonstrated that the experimental group significantly improved writing proficiency, showing a reduction in common errors (third-person singular present, past tense, progressive, past participle, plural, possessive, comparative, and superlative) compared to the control group. Furthermore, most students preferred AI feedback, associating it with noticeable improvements in their writing skills and grammatical accuracy. These findings support the integration of AI tools like ChatGPT into language learning curricula as effective supplements to traditional teaching methods, offering personalized and immediate corrections that enhance learning outcomes.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Across writing, reading, and mathematics tasks, students repeatedly submit work to AI systems, receive concrete suggestions, and resubmit revised work, creating a cycle of practice, feedback, and renewed practice.
“Across writing, reading, and mathematics tasks, students repeatedly submit texts, assignments, or answers to AI systems, receive concrete suggestions on error correction, structure, and language use, and then resubmit revised work, creating a cycle of practice, feedback, and renewed practice [75,77,82,83,87,90,110].”
From A Systematic Review of Generative AI in K–12: Mapping Goals, Activities, Roles, and Outcomes via the 3P Model (2025) · cites this paper as [87]
Section 3.2 describes students entering English stories into ChatGPT, receiving grammatical and structural feedback, and revising their stories. The source does not establish the same cycle for reading or mathematics tasks, or say that students resubmitted their revised stories to ChatGPT. (LLM, conf=0.88)
Experimental — accuracy not yet measuredAI provides strong scaffolds for core practices, markedly improving the quality and conventionality of learner outputs-for example, enhancing grammatical accuracy and argumentative coherence in writing, and supporting problem-solving and experimental design in science and mathematics-thereby helping learners meet baseline practice demands more efficiently.
“First, AI provides strong scaffolds for core practices, markedly improving the quality and conventionality of learner outputs-for example, enhancing grammatical accuracy and argumentative coherence in writing [86,87,145], and supporting problem-solving and experimental design in science and mathematics [77,88,93,103,147]-thereby helping learners meet baseline practice demands more efficiently.”
From A Systematic Review of Generative AI in K–12: Mapping Goals, Activities, Roles, and Outcomes via the 3P Model (2025) · cites this paper as [87]
The Discussion reports improved grammatical precision in English learners’ writing following ChatGPT feedback. Section 2.3 describes coherent essay structure in a study the paper reviews, but the cited paper does not establish improved argumentative coherence specifically. The science and mathematics examples have separate citations and are not attributed to this source. (LLM, conf=0.84)
Experimental — accuracy not yet measuredSome studies document confusion, frustration, and other negative emotions driven by mistrust, technical limits, or unmet expectations, and even declines in self-efficacy.
“Some studies document confusion, frustration, and other negative emotions driven by mistrust, technical limits, or unmet expectations [78,87,93,98], and even declines in self-efficacy [140].”
From A Systematic Review of Generative AI in K–12: Mapping Goals, Activities, Roles, and Outcomes via the 3P Model (2025) · cites this paper as [87]
The Discussion reports that several learners were dissatisfied with ChatGPT’s limited adaptability, supporting a narrow part of the claim about negative reactions to a technical limitation. It does not report confusion, frustration, or mistrust, and it says learners’ confidence improved rather than documenting a decline in self-efficacy. No page number is available in our copy. (LLM, conf=0.84)
Experimental — accuracy not yet measuredNumerous studies report higher enthusiasm, participation, curiosity, and satisfaction after AI use, alongside a general preference for AI tools as efficient and convenient.
“Numerous studies report higher enthusiasm, participation, curiosity, and satisfaction after AI use [6,70,74,81,87,91,92,101,104,106,113,114,116,119,131,141,142], alongside a general preference for AI tools as efficient and convenient [99,111,124,127,135,140].”
From A Systematic Review of Generative AI in K–12: Mapping Goals, Activities, Roles, and Outcomes via the 3P Model (2025) · cites this paper as [87]
The Discussion and Conclusion (pages not provided) report greater motivation, engagement, enjoyment, and satisfaction among ESL learners using ChatGPT, supporting much of the first, citation-linked clause. The paper does not report increased curiosity specifically. The efficiency-and-convenience clause has a separate citation group and is not assessed here. (LLM, conf=0.82)
Experimental — accuracy not yet measuredStudies used AI interventions to address common barriers such as limited teacher feedback, low student motivation for revision, or insufficient opportunities for creative expression.
“These studies used AI interventions to address common barriers such as limited teacher feedback, low student motivation for revision, or insufficient opportunities for creative expression [81-87].”
From A Systematic Review of Generative AI in K–12: Mapping Goals, Activities, Roles, and Outcomes via the 3P Model (2025) · cites this paper as [87]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
The publisher hasn’t deposited this paper’s reference list.
Research works printed but not linked: 7
- R. Ellis, Second Language Acquisition. The United States: Oxford, 1997.
- E. Hidayatullah, "Evaluating the effectiveness of ChatGPT to improve English students' writing skills," Heal, vol. 1, no. 1, pp. 14-19, 2024. https://doi.org/10.36597/heal.v1i1.1467 · DOI
- Ž. Bašić, A. Banovac, I. Kružić, and I. Jerković, "ChatGPT-3.5 as writing assistance in stu- dents' essays," Humanities and Social Sciences Communications, vol. 10, 2023. https://doi. org/10.1057/s41599-023-02269-7 · DOI · Paper page
- N. Y. Kim, Y. Cha, and H. S. Kim, "Future English learning: Chatbots and artificial intelli- gence," Multimedia Assisted Language Learning, vol. 22, no. 3, pp. 32-53, 2019. https://doi. org/10.15702/mall.2019.22.3.32 · DOI
- S. Mahapatra, "Impact of ChatGPT on ESL students' academic writing skills: A mixed methods intervention study," Smart Learning Environments, vol. 11, 2024. https://doi. org/10.1186/s40561-024-00295-9 · DOI · Paper page
- J. A. Z. Zebua and C. V. Katemba, "Students' perceptions of using the OpenAI ChatGPT application in improving writing skills," Journal of Language and Literature Studies, vol. 4, no. 1, pp. 110-123, 2024. https://doi.org/10.36312/jolls.v4i1.1805 · DOI
- A. Rahma and R. Fithriani, "The potential impact of using ChatGPT on EFL students' writing: EFL teachers' perspective," Indonesian EFL Journal, vol. 10, no. 1, pp. 11-20, 2024. https://journal.uniku.ac.id/index.php/IEFLJ/article/view/9222
Cited by
Sorted by citations
Lin, X., & Tan, H. (2025) · Systems · doi:10.3390/systems13100840 · Cited by 22 · see citing works
Abduljawad, S. A. (2025) · International Journal of Computer-Assisted Language Learning and Teaching · doi:10.4018/ijcallt.367276 · Cited by 19 · see citing works
Muthmainnah, M., Asad, M. M., Yakin, A. M. A., & Almusharraf, N. (2025) · Asian Education and Development Studies · doi:10.1108/aeds-01-2025-0038 · Cited by 14 · see citing works
Mohamed, A., Elasad, A., Fuad, U., Pengas, I. P., Elsayed, A., Bhamidipati, P., & Salib, P. (2025) · Cureus · doi:10.7759/cureus.92280 · Cited by 16 · see citing works
“This function is particularly valuable for non-English speakers who struggle with academic writing [88].”
Pretorius, M., & Thewissen, J. (2026) · Journal of Second Language Writing · doi:10.1016/j.jslw.2026.101286 · Cited by 15 · see citing works
LLM-generated formative feedback in education: A qualitative systematic literature review
Maier, U., Seibold, M., & Klotz, C. (2026) · Computers and Education Open · doi:10.1016/j.caeo.2026.100374 · Cited by 10 · see citing works
Can ChatGPT score ESL writing? A correlation analysis between teacher and GenAI scores
Alkhofi, A. (2026) · Language Teaching Research · doi:10.1177/13621688261415584 · Cited by 4 · see citing works
Zhang, J., Zhang, L. J., & Wang, X. (2026) · Educational Studies · doi:10.1080/03055698.2026.2698519 · Cited by 3 · see citing works
Comparing AI and human feedback at higher education: Level appropriateness, quality and coverage
Cengiz, Y., & Yiğitoğlu, N. (2025) · Language Teaching · doi:10.1017/s0261444825000199 · Cited by 5 · see citing works
“Our findings align with those of the literature, showing that AI tools can effectively provide corrective feedback (Jamshed et al., 2024), particularly when context relevant prompts are utilized (Venter et al., 2024).”
Comparing Teacher and ChatGPT Feedback in EFL/ESL Writing
Hamzehloo, M., Azar, A. S., & Hamzehloo, M. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-5601-3.ch007 · Cited by 1 · see citing works
Does ChatGPT-Integrated Learning Affect Indonesian EFL Learners’ Grammar Achievement?
Azwar, T. A., & Sujarwati, I. (2025) · ELE Reviews English Language Education Reviews · doi:10.22515/elereviews.v5i1.10425 · Cited by 6 · see citing works
“Meanwhile, few studies have involved secondary-level EFL students (Aldowsari & Aljebreen, 2024; Jamshed et al., 2024; Sapan & Uzun, 2024).”
Mobile-Assisted Language Learning
Stockwell, G. (2025) · Elsevier eBooks · doi:10.1016/b978-0-323-95504-1.00524-x
AI-Facilitated Formative Assessment
Kishore, S. (2025) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-1952-0.ch004
Dida-Agun, A., & Abarquez, C. A. (2025) · Psychology and Education A Multidisciplinary Journal · doi:10.70838/pemj.460408 · Cited by 1 · see citing works
ChatGPT and Adult English Language Learning: A Scoping Literature Review
Askari, M., & Yazdani, J. (2026) · New Horizons in Adult Education and Human Resource Development · doi:10.1177/19394225261454716
Lin, H. P.-S., Ngo, T. T.-N., & Chen, H. H.-J. (2026) · English Teaching & Learning · doi:10.1007/s42321-026-00236-4
Leonard, D., Gole, R., & Dacon, J. (2026) · ACM Conference on Learning @ Scale (L@S) · doi:10.1145/3774398.3811611
Hidayat, N., Ibrahim, S. A., Pramukti, A. R. D., Arifani, Y., & Wijayatiningsih, T. D. (2026) · Human Behavior and Emerging Technologies · doi:10.1155/hbe2/1167530 · Cited by 1 · see citing works
Ismail, I. H., Said, N. B., & Ting, P. D. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-33997-3_1
Torres-Vásquez, L., & Christie, D. E. V. (2026) · Ampersand · doi:10.1016/j.amper.2026.100283
Long-term impact of ChatGPT feedback on EFL students' writing skills development accross genres
Fatmawati, Basthomi, Y., Suryati, N., Laksmi, E. D., & Hassan, I. (2026) · Multidisciplinary Science Journal · doi:10.31893/multiscience.2027179
“These findings align with the results of prior studies (Fan, 2023a; Jamshed et al. 2024; Taskiran et al. 2024), which emphasize that while AI-generated feedback is effective, its success depends on students’ language proficiency and their ability to interpret suggestions accurately.”
A Qualitative Survey on How ChatGPT Improve Students’ Confidence
Zakaria, S. K. (2026) · Studies in big data · doi:10.1007/978-3-032-20412-7_73
Duong, H. T. M., Pham, C. K., & Duong, H. T. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-41317-8_11
- Authors
- Jamshed, M., Ahmed, A. S. M. M., Sarfaraj, M., & Warda, W. U.
- Affiliations
- Prince Sattam Bin Abdulaziz University (SA)
- Chaitanya Bharathi Institute of Technology (IN)
- Venue
- International Journal of Interactive Mobile Technologies (iJIM)
- Published
- 2024-10-03
- Volume
- 18
- Issue
- 19
- Pages
- 18-36
- ISSN
- 1865-7923 (ISSN-L)
- OpenAlex
- W4403104819
- Cited by
- 24
- References
- 0
- Citations by year
- 2026: 15 · 2025: 9
- FWCI
- 37.62
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- International Journal of Interactive Mobile Technologies (iJIM) (publishedVersion, cc-by)
- Topics
- Social Sciences › Arts and Humanities › Language and Linguistics › EFL/ESL Teaching and Learning
- Physical Sciences › Computer Science › Information Systems › English Language Learning and Teaching
- Physical Sciences › Computer Science › Information Systems › Artificial Intelligence in Education
- Keywords
- ChatGPT, English as a second language, AI-generated feedback, teacher feedback, grammatical accuracy, student attitudes toward AI, writing skills
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
