Integrating ChatGPT into EFL writing instruction: Benefits and challenges
Open accessAbstract
Teaching English as a Foreign Language (EFL) writing skills presents a unique set of challenges, from developing students' language proficiency to providing personalized feedback and support. In recent years, there has been growing interest in the potential of AI and NLP, such as ChatGPT, to support language education. This paper explores the potential benefits and challenges of using ChatGPT in EFL writing instruction. This paper is based on a review of relevant literature and highlights the potential of ChatGPT for EFL writing students. ChatGPT's ability to generate human-like text based on the input it receives makes it a potentially helpful tool for supporting students in their writing practice. Its natural language capabilities can engage and motivate learners. However, the potential challenges of using ChatGPT in language education are also discussed, such as the design, implementation and potential ethical concerns. This paper aims to provide a comprehensive overview of the potential benefits and challenges of integrating ChatGPT into EFL writing instruction. By exploring the potential of ChatGPT as a tool for language education, we aim to contribute to the ongoing debate on the role of technology and provide guidance for educators interested in using ChatGPT in their classrooms.
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?
While ChatGPT enhanced efficiency and confidence, its limitations became apparent in areas demanding creativity, critical thinking, and personal voice.
“While the tool enhanced efficiency and confidence, its limitations became apparent in areas demanding creativity, critical thinking, and personal voice, concerns echoed in Baskara (2023) and Niloy et al. (2024).”
From An Investigation into the Usage of ChatGPT in Academic Writing by EFL University Students in North and East Syria: A Cross-Sectional Study (2025) · cites this paper as Baskara (2023)
Section 3.1 says ChatGPT may struggle to support writing tasks requiring creativity or originality, echoing that part of the concern. The passages do not address limitations involving critical thinking or personal voice. The citing sentence presents efficiency and confidence as its own finding, not as a finding attributed to Baskara. (LLM, conf=0.85)
Experimental — accuracy not yet measuredIf ChatGPT's training data is not diverse or representative, the tool can produce biased outputs that affect both quality and reliability.
“Baskara (2023) cautions that if the training data is not diverse or representative, the tool can produce biased outputs that affect both quality and reliability.”
From An Investigation into the Usage of ChatGPT in Academic Writing by EFL University Students in North and East Syria: A Cross-Sectional Study (2025) · cites this paper as Baskara (2023)
ChatGPT's capacity to generate human-like texts can serve as a source of motivation for students, guiding them in vocabulary, grammar, and syntax.
“As Baskara (2023) points out, ChatGPT's capacity to generate human-like texts can serve as a source of motivation for students, guiding them in areas such as vocabulary, grammar, and syntax.”
From An Investigation into the Usage of ChatGPT in Academic Writing by EFL University Students in North and East Syria: A Cross-Sectional Study (2025) · cites this paper as Baskara (2023)
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
Bender, E. M., & Friedman, B. (2018) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00041 · Cited by 854 · cited 1× · see citing works
“In addition, if the training data does not represent different genders, ages, or other demographic factors, this can also introduce bias into the text generated by the technology [46].”
BackgroundTechnology and the future of language teaching
Kessler, G. (2018) · Foreign Language Annals · doi:10.1111/flan.12318 · Cited by 529 · see citing works
Designing Effective Feedback Processes in Higher Education: A Learning-Focused Approach
Winstone, N., & Carless, D. (2019) · doi:10.4324/9781351115940 · Cited by 373 · see citing works
The challenges of feedback in higher education
Henderson, M., Ryan, T., & Phillips, M. (2019) · Assessment & Evaluation in Higher Education · doi:10.1080/02602938.2019.1599815 · Cited by 335 · see citing works
Flagged first, then by citations
Research works printed but not linked: 42
- A. A. Menbet, "The Use of Effective Strategies to Improve Saudi EFL Dyslexic Learners' Writing Skills," Theory Pract. Lang. Stud., vol. 8, no. 12, pp. 1611-1621, Dec. 2018, doi: 10.17507/tpls.0812.06. · DOI
- A. A. Patak et al., "Teaching English as a Foreign Language in Indonesia: University Lecturers' Views on Plagiarism," J. Acad. Ethics, pp. 1-17, 2020, doi: 10.1007/s10805-020-09385-y. · DOI
- M. G. Salaxiddinovna, "Solutions to the problems of teaching writing skills in English in higher education institutions based on foreign manuals," Web Sci. Int. Sci. Res. J., vol. 3, no. 6, pp. 1782-1785, 2022.
- L. J. Z. Tingting Zhang, "Taking Stock of a Genre-Based Pedagogy: Sustaining the Development of EFL Students' Knowledge of the Elements in Argumentation and Writing Improvement," Sustainability, vol. 13, no. 21, p. 11616, Oct. 2021, doi: 10.3390/su132111616. · DOI
- K. H. Hidayati, "Teaching Writing to EFL Learners: An Investigation of Challenges Confronted by Indonesian Teachers," Langkawi J. Assoc. Arab. English, vol. 4, no. 1, pp. 21-31, Jun. 2018, doi: 10.31332/lkw.v4i1.772. · DOI
- Y. Cheng, "Paths to Improve the Language Communicative Competence and Accomplishment for Foreign Language Professional Students," in 3rd International Proceedings on Conference on Economics, Management Engineering and Education Technology, 2019, pp. 2298-2302.
- R. Al-Jarf, "Integrating participation goals in writing activities for EFL college students," J. Res. Sch. Prof. English Lang. Teach., vol. 5, no. 23, pp. 1-11, 2021.
- R. Wanchid, "The Use of Self-Correction, Paper-pencil Peer Feedback and Electronic Peer Feedback in the EFL Writing Class: Opportunities and Challenges," Acad. J. Interdiscip. Stud., vol. 2, no. 3, pp. 157- 157, Nov. 2013, doi: 10.5901/ajis.2013.v2n3p157. · DOI
- K. Wang, "Problems and tactics in Peer feedback in EFL Writing Teaching," in Proceedings of the International Conference on Education, Management and Information Technology, 2015, pp. 480-483, doi: 10.2991/icemit-15.2015.101. · DOI
- W.-C. V. Wu, J.-C. Yang, J. S. C. Hsieh, and T. Yamamoto, "Free from demotivation in EFL writing: the use of online flipped writing instruction," Comput. Assist. Lang. Learn., vol. 33, no. 4, pp. 353-387, May 2020, doi: 10.1080/09588221.2019.1567556. · DOI
- P. Kawinkoonlasate, "A Study of Using E-Writing Instructional Design Program to Develop English Writing Ability of Thai EFL Learners," English Lang. Teach., vol. 14, no. 6, p. 43, May 2021, doi: 10.5539/elt.v14n6p43. · DOI
- U. C. Okonkwo, "Computer Assisted Language Learning (CALL) Software: Evaluation of its Influence in a Language Learning Process," UJAH Unizik J. Arts Humanit., vol. 12, no. 1, pp. 76-89, Nov. 2011, doi: 10.4314/ujah.v12i1.4. · DOI
- L. Jin and E. Deifell, "Foreign Language Learners' Use and Perception of Online Dictionaries: A Survey Study," J. Online Learn. Teach., vol. 9, no. 4, pp. 515-533, Jan. 2013.
- R. Godwin-Jones, "Emerging Technologies: Mobile Apps for Language Learning," Lang. Learn. Technol., vol. 15, no. 2, pp. 2-11, Jun. 2011.
- A. Pardo, J. Jovanovic, S. Dawson, D. Gasevic, and N. Mirriahi, "Using Learning Analytics to Scale the Provision of Personalised Feedback.," Br. J. Educ. Technol., vol. 50, no. 1, pp. 128-138, Jan. 2019, doi: 10.1111/bjet.12592. · DOI · Paper page
- R. C. Sharma and Y. Sharma, "Augmenting Learning through Virtual Reality Applications in Education," in Tenth Pan-Commonwealth Forum on Open Learning, 2022, pp. 1-6, doi: 10.56059/pcf10.7986. · DOI
- L. K. Fryer, K. Nakao, and A. Thompson, "Chatbot learning partners: Connecting learning experiences, interest and competence," Comput. Human Behav., vol. 93, pp. 279-289, Apr. 2019, doi: 10.1016/j.chb.2018.12.023. · DOI · Paper page
- G.-J. Hwang, H. Xie, B. W. Wah, and D. Gasevic, "Vision, challenges, roles and research issues of Artificial Intelligence in Education," Comput. Educ. Artif. Intell., vol. 1, p. 100001, 2020, doi: 10.1016/j.caeai.2020.100001. · DOI · Paper page
- B. H. Khan, Managing e-learning: design, delivery, implementation and evaluation. London: Information Science Publishing, 2005. doi: 10.4018/978-1-59140-634-1 · DOI
- M. Warschauer and C. Meskill, "Technology and Second Language Teaching," in Handbook of undergraduate second language education, New York: Routledge Taylor & Francis Group, 2000, pp. 303-318.
- R. Zhang and D. Zou, "Types, purposes, and effectiveness of state-of-the-art technologies for second and foreign language learning," Comput. Assist. Lang. Learn., pp. 1-47, Apr. 2020, doi: 10.1080/09588221.2020.1744666. · DOI
- N. Mehrabi, F. Morstatter, N. Saxena, K. Lerman, and A. Galstyan, "A Survey on Bias and Fairness in Machine Learning," ACM Comput. Surv., vol. 54, no. 6, pp. 1-35, Jul. 2022, doi: 10.1145/3457607. · DOI · Paper page
- H. A. Alamri, H. Alamri, S. L. Watson, and W. R. Watson, "Learning Technology Models That Support Personalization within Blended Learning Environments in Higher Education.," Techtrends, vol. 65, no. 1, pp. 62-78, Jan. 2021, doi: 10.1007/s11528-020-00530-3. · DOI
- C. D. Schunn, "Peer feedback and teacher feedback: a comparative study of revision effectiveness in writing instruction for EFL learners," High. Educ. Res. Dev., pp. 1-17, Sep. 2021, doi: 10.1080/07294360.2021.1969541. · DOI · Paper page
- S. Yu, F. Geng, C. Liu, and Y. Zheng, "What works may hurt: The negative side of feedback in second language writing," J. Second Lang. Writ., vol. 54, p. 100850, Dec. 2021, doi: 10.1016/j.jslw.2021.100850. · DOI
- M. Selvaraj and A. A. Aziz, "Systematic Review: Approaches in Teaching Writing Skill in ESL Classrooms," Int. J. Acad. Res. Progress. Educ. Dev., vol. 8, no. 4, pp. 450-473, Nov. 2019, doi: 10.6007/ijarped/v8-i4/6564. · DOI
- I. Lee, "Teacher Written Corrective Feedback: Less Is More.," Lang. Teach., vol. 52, no. 4, pp. 524-536, Oct. 2019, doi: 10.1017/s0261444819000247. · DOI
- S. Çelik, "Building Critical Academic Writing Skills: The Impact of Instructor Feedback on Turkish ELT Graduate Students.," TESL-EJ, vol. 24, no. 3, p. n3, 2020.
- D. Jackson and K. Usher, "Feeding Back and Feeding Forward," Success. Dr. Train. Nurs. Heal. Sci., pp. 71-82, Dec. 2021, doi: 10.1007/978-3-030-87946-4_5. · DOI
- I. Ibacache Calderón and D. Campos Galdames, "Feedback in virtual times: a challenge when teaching EFL writings," Feed. virtual times a Chall. when Teach. EFL writings, pp. 49-57, 2021. doi: 10.2307/j.ctv20hcv1n.7 · DOI
- Y. Han and Y. Xu, "The development of student feedback literacy: the influences of teacher feedback on peer feedback," Assess. Eval. High. Educ., vol. 45, no. 5, pp. 680-696, Jul. 2020, doi: 10.1080/02602938.2019.1689545. · DOI
- V. Toro, G. Camacho-Minuche, E. Pinza-Tapia, and F. M. Paredes, "The Use of the Communicative Language Teaching Approach to Improve Students' Oral Skills.," English Lang. Teach., vol. 12, no. 1, pp. 110-118, Dec. 2018, doi: 10.5539/elt.v12n1p110. · DOI
- G. Cheng and G. S. M. Chwo, "Automated tracking of student revisions in response to teacher feedback in EFL writing: technological feasibility and teachers' perspectives," Interact. Learn. Environ., pp. 1-25, Nov. 2021, doi: 10.1080/10494820.2021.2001539. · DOI
- W. Zheng, H. Cheng, J. X. Yu, L. Zou, and K. Zhao, "Interactive natural language question answering over knowledge graphs," Inf. Sci. (Ny)., vol. 481, pp. 141-159, May 2019, doi: 10.1016/j.ins.2018.12.032. · DOI
- T.-H. Nguyen, W.-Y. Hwang, X.-L. Pham, and T. Pham, "Self-experienced storytelling in an authentic context to facilitate EFL writing," Comput. Assist. Lang. Learn., pp. 1-30, Apr. 2020, doi: 10.1080/09588221.2020.1744665. · DOI
- S. Thongchalerm and W. Jarunthawatchai, "The Impact of Genre Based Instruction on EFL Learners' Writing Development.," Int. J. Instr., vol. 13, no. 1, pp. 1-16, Jan. 2020, doi: 10.29333/iji.2020.1311a. · DOI
- K. Hyland and F. Hyland, Feedback in Second Language Writing. Cambridge University Press, 2019. doi: 10.1017/9781108635547 · DOI
- K. J. Hartshorn, N. W. Evans, P. F. Merrill, R. R. Sudweeks, D. Strong-Krause, and N. J. Anderson, "Effects of dynamic corrective feedback on ESL writing accuracy," Tesol Q., vol. 44, no. 1, pp. 84-109, 2010, doi: 10.5054/tq.2010.213781. · DOI
- K. Barkaoui, "Teaching Writing to Second Language Learners: Insights from Theory and Research," TESL Report., vol. 40, no. 1, pp. 35-48, Jan. 2007.
- H. Benbya, T. H. Davenport, and S. Pachidi, "Artificial Intelligence in Organizations: Current State and Future Opportunities," MIS Q. Exec., vol. 19, no. 4, pp. 1-15, 2020, doi: 10.2139/ssrn.3741983. · DOI
- M. Mnasri, "Recent advances in conversational NLP : Towards the standardization of Chatbot building.," arXiv: Computation and Language. pp. 1-8, Mar-2019, doi: 10.48550/arXiv.1903.09025. · DOI
- S. Singh and H. K. Thakur, "Survey of Various AI Chatbots Based on Technology Used," 2020 8th Int. Conf. Reliab. Infocom Technol. Optim. (Trends Futur. Dir., pp. 1074-1079, 2020, doi: 10.1109/icrito48877.2020.9197943. · DOI
Cited by
Sorted by citations
Alkamel, M. A. A., & Alwagieh, N. A. S. (2024) · Social Sciences & Humanities Open · doi:10.1016/j.ssaho.2024.101095 · Cited by 41 · see citing works
Shen, Y., & Chen, L. (2026) · Computer Assisted Language Learning · doi:10.1080/09588221.2025.2479141 · Cited by 30 · see citing works
(2024) · Annals of Human and Social Sciences · doi:10.35484/ahss.2024(5-i)39 · Cited by 25 · see citing works
Othman, N. A. (2025) · TESOL Today · doi:10.53898/tesol2025215 · Cited by 2 · see citing works
- Authors
- Baskara, F. R.
- Affiliations
- Swinburne University of Technology (AU)
- Corresponding author
- Baskara, FX Risang
- ORCID
- Baskara, FX Risang
- Venue
- International Journal of Education and Learning
- Publisher
- ASCEE Publications
- Published
- 2023-04-30
- Volume
- 5
- Issue
- 1
- Pages
- 44-55
- ISSN
- 2684-9240 (ISSN-L)
- OpenAlex
- W4392898788
- Cited by
- 118
- References
- 4
- Citations by year
- 2026: 30 · 2025: 47 · 2024: 37 · 2023: 4
- FWCI
- 21.35
- Type
- journal article
- Language
- en
- Open access
- diamond
- doi.org
- Licence
- Locations
- International Journal of Education and Learning (publishedVersion, cc-by-sa)
- Universitas Sanata Dharma Repository (Universitas Sanata Dharma) (acceptedVersion)
- Topics
- Physical Sciences › Computer Science › Information Systems › Artificial Intelligence in Education
- Physical Sciences › Computer Science › Information Systems › English Language Learning and Teaching
- Social Sciences › Arts and Humanities › Language and Linguistics › EFL/ESL Teaching and Learning
- Keywords
- ChatGPT, EFL writing instruction, artificial intelligence in language teaching, writing feedback, student motivation, AI ethics, technology integration in classrooms, natural language processing
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
