A Systematic Review of ChatGPT for English as a Foreign Language Writing: Opportunities, Challenges, and Recommendations
Open accessThe DOI matches its Crossref record; 24 of the 24 references it cites were found in a registry or an index.
Abstract
Since its release in November 2022, ChatGPT has become a focal point of discussion among scholars and practitioners.This study investigates the role of ChatGPT in English as a Foreign Language (EFL) writing through a systematic review of the 20 most pertinent articles.Inclusion and exclusion of references were based on the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines.Findings suggest that the integration of artificial intelligence (AI) into education is an evolving process that significantly impacts how EFL students learn to write.This systematic review highlights both the opportunities and challenges associated with adopting ChatGPT for EFL writing.On one hand, ChatGPT offers innovative ways to enhance writing skills, providing instant feedback and diverse writing prompts.On the other hand, challenges such as dependency on AI and the need for critical thinking skills remain.Based on the synthesized literature, recommendations for EFL teaching were proposed, emphasizing a balanced approach to integrating AI tools like ChatGPT into writing curricula and creating a community of practice among teachers and students.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
What is AI Literacy? Competencies and Design Considerations
Long, D., & Magerko, B. (2020) · Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3313831.3376727 · Cited by 3,241 · cited 2×
“…as the competencies needed to interact effectively with both humans and machines, including the knowledge and skills that enable humans to critically understand, evaluate, and use AI systems and tools to safely and ethically participate in an increasingly digital world (Long & Magerko, 2020).”
BackgroundWhat if the devil is my guardian angel: ChatGPT as a case study of using chatbots in education
Tlili, A., Shehata, B., Adarkwah, M. A., Bozkurt, A., Hickey, D. T., Huang, R., & Agyemang, B. (2023) · Smart Learning Environments · doi:10.1186/s40561-023-00237-x · Cited by 2,003 · cited 1×
“Tlili et al. (2023) analyzed tweets and interviews with stakeholders, revealing mixed reactions to the potential uses and misuses of these technologies.”
BackgroundChatGPT: Bullshit spewer or the end of traditional assessments in higher education?
(2023) · Journal of Applied Learning & Teaching · doi:10.37074/jalt.2023.6.1.9 · Cited by 1,806 · cited 1×
“AI tools like ChatGPT are prompting much-needed innovation in assessment and teaching methods (Rudolph et al., 2023).”
MethodArtificial intelligence in education: Addressing ethical challenges in K-12 settings
Akgun, S., & Greenhow, C. (2022) · AI and Ethics · doi:10.1007/s43681-021-00096-7 · Cited by 1,473
ChatGPT for Language Teaching and Learning
Kohnke, L., Moorhouse, B. L., & Zou, D. (2023) · RELC Journal · doi:10.1177/00336882231162868 · Cited by 1,371 · cited 1×
“ChatGPT, an open-access and sophisticated chatbot powered by GPT technology, has significantly transformed language teaching and learning (Kohnke et al., 2023).”
BackgroundThe promises and challenges of artificial intelligence for teachers: A systematic review of research
Celik, I., Dindar, M., Muukkonen, H., & Järvelä, S. (2022) · TechTrends · doi:10.1007/s11528-022-00715-y · Cited by 984 · cited 1×
“Celik et al. (2022) conducted a comprehensive analysis to investigate the potential and challenges of AI in teaching practices from the perspectives of teachers and their roles in AI-based education research.”
BackgroundUsing ChatGPT for second language writing: pitfalls and potentials
Barrot, J. S. (2023) · Assessing Writing · doi:10.1016/j.asw.2023.100745 · Cited by 770 · cited 3×
“The collection and analysis of data by AI tools, including ChatGPT, pose risks, and over-reliance on technology may also diminish the importance of human interaction and mentorship in learning to write (Barrot, 2023).”
BackgroundMethodSong, C., & Song, Y. (2023) · Frontiers in Psychology · doi:10.3389/fpsyg.2023.1260843 · Cited by 717
Impact of ChatGPT on learners in a L2 writing practicum: an exploratory investigation
Yan, D. (2023) · Education and Information Technologies · doi:10.1007/s10639-023-11742-4 · Cited by 713 · cited 1×
“Yan (2023) and Guo and Wang (2024) examined ChatGPT’s role in providing extensive and balanced feedback, surpassing human feedback in some areas.”
BackgroundExploring the potential of using an AI language model for automated essay scoring
Mizumoto, A., & Eguchi, M. (2023) · Research Methods in Applied Linguistics · doi:10.1016/j.rmal.2023.100050 · Cited by 647
Comparing the quality of human and ChatGPT feedback of students’ writing
Steiss, J., Tate, T., Graham, S., Cruz, J., Hebert, M., Wang, J., Moon, Y., Tseng, W., Warschauer, M., & Olson, C. B. (2024) · Learning and Instruction · doi:10.1016/j.learninstruc.2024.101894 · Cited by 509 · cited 1×
“Even more recent studies, particularly those published in 2024 (e.g., Steiss et al., 2024), have accumulate citations, reflecting the attention to this topic of ChatGPT in EFL writing.”
ResultGuo, K., & Wang, D. (2024) · Education and Information Technologies · doi:10.1007/s10639-023-12146-0 · Cited by 449 · cited 5×
“Such collaborative efforts align with the concept of collegial inquiry, where teachers and students work together to explore and develop more complex perspectives, thereby enhancing engagement in writing (Guo & Wang, 2024; Woo et al., 2024).”
BackgroundInfluentialImran, M., & Almusharraf, N. (2023) · Contemporary Educational Technology · doi:10.30935/cedtech/13605 · Cited by 421
Impact of ChatGPT on ESL students’ academic writing skills: a mixed methods intervention study
Mahapatra, S. (2024) · Smart Learning Environments · doi:10.1186/s40561-024-00295-9 · Cited by 398
García-Peñalvo, F. J. (2023) · Education in the Knowledge Society (EKS) · doi:10.14201/eks.31279 · Cited by 331
Digital support for academic writing: A review of technologies and pedagogies
Strobl, C., Ailhaud, E., Benetos, K., Devitt, A., Kruse, O., Proske, A., & Rapp, C. (2019) · Computers & Education · doi:10.1016/j.compedu.2018.12.005 · Cited by 298 · cited 2×
“Digitalized writing represents a major shift in the process of writing, which remains a fundamental mode of expression and learning (Strobl et al., 2019).”
BackgroundTeng, M. F. (2024) · Computers and Education: Artificial Intelligence · doi:10.1016/j.caeai.2024.100270 · Cited by 182 · cited 10×
“Similarly, Teng (2024) highlighted that AI assistance significantly boosted writing motivation and self-efficacy among Chinese students.”
BackgroundInfluentialSelf-citationA Preliminary Investigation of Fake Peer-Reviewed Citations and References Generated by ChatGPT
Day, T. (2023) · The Professional Geographer · doi:10.1080/00330124.2023.2190373 · Cited by 160 · cited 2×
“The ease of generating content with ChatGPT could lead to misuse, such as creating misleading or plagiarized content, including false citations (Day, 2023).”
BackgroundAI-writing tools in education: If you can’t beat them, join them
Tseng, W., & Warschauer, M. (2023) · Journal of China Computer-Assisted Language Learning · doi:10.1515/jccall-2023-0008 · Cited by 119 · cited 1×
“The development of writing lessons within the EFL curriculum reflects the AI literacy framework, which comprises five essential elements: understanding, accessing, prompting, corroborating, and incorporating (Tseng & Warschauer, 2023).”
BackgroundCultivating writing skills: The role of ChatGPT as a learning assistant—A case study
Punar Özçelik, N., & Yangın Ekşi, G. (2024) · Smart Learning Environments · doi:10.1186/s40561-024-00296-8 · Cited by 115 · cited 2×
“Theme 4: ChatGPT on Writing Improvement Punar Özçelik and Yangın Ekşi (2024) conducted a case study examining the role of ChatGPT in cultivating writing skills, particularly in acquiring register knowledge across various writing tasks.”
BackgroundMethodAlgorithmic Literacy and the Role for Libraries
Ridley, M., & Pawlick-Potts, D. (2021) · Information Technology and Libraries · doi:10.6017/ital.v40i2.12963 · Cited by 111 · cited 1×
“Ridley and Pawlick-Potts (2021) offered another definition focused on algorithmic literacy, which includes the skills, expertise, and awareness needed to understand and reason about algorithms, recognize and interpret their use in systems, create and apply algorithmic techniques to various…”
BackgroundTesting the viability of ChatGPT as a companion in L2 writing accuracy assessment
Mizumoto, A., Shintani, N., Sasaki, M., & Teng, M. F. (2024) · Research Methods in Applied Linguistics · doi:10.1016/j.rmal.2024.100116 · Cited by 104
Self-citationWoo, D. J., Wang, D., Guo, K., & Susanto, H. (2024) · Education and Information Technologies · doi:10.1007/s10639-024-12819-4 · Cited by 104 · cited 2×
“However, some challenges remain, such as ChatGPT’s limitations in detecting deep structure and pragmatic errors (Al-Garaady & Mahyoob, 2023) and its potential to impose heavy cognitive demands on learners (Woo et al., 2024).”
BackgroundChatGPT and the digitisation of writing
Zhao, X., Cox, A., & Cai, L. (2024) · Humanities and Social Sciences Communications · doi:10.1057/s41599-024-02904-x · Cited by 93 · cited 2×
“Using Long and Magerko’s (2020) framework, Zhao et al. (2024) updated the notion of AI literacy to include generative AI literacy, which might be defined through several dimensions: pragmatic understanding, safety understanding, reflective understanding, socio-ethical understanding, and contextual…”
Method
Cited by
Teng, M. F. (2024) · Computers and Education: Artificial Intelligence · doi:10.1016/j.caeai.2024.100270 · Cited by 182
Self-citationGenerative AI (GenAI) in the language classroom: A systematic review
Lee, S., Choe, H., Zou, D., & Jeon, J. (2026) · Interactive Learning Environments · doi:10.1080/10494820.2025.2498537 · Cited by 158
Sardi, J., Darmansyah, Candra, O., Yuliana, D. F., Habibullah, Yanto, D. T. P., & Eliza, F. (2025) · International Journal of Engineering Pedagogy (iJEP) · doi:10.3991/ijep.v15i1.53379 · Cited by 105
Tran, T. T. T. (2025) · Education Sciences · doi:10.3390/educsci15020232 · Cited by 68
“Moreover, there is a risk of difficulty in understanding and comprehending responses as well as providing inaccurate feedback, which may confuse learners rather than support their writing development (Teng, 2024).”
Incorporating ChatGPT for EFL Writing and Its Effects on Writing Engagement
Teng, M. F., & Huang, J. (2025) · International Journal of Computer-Assisted Language Learning and Teaching · doi:10.4018/ijcallt.367874 · Cited by 53
Self-citation
Metadata
- Venue
- International Journal of TESOL Studies
- Publisher
- International TESOL Union
- Published
- 2024-07-01
- ISSN
- 2632-6779 (ISSN-L)
- 2633-6898
- OpenAlex
- W4400220252
- Cited by
- 87
- References
- 24
- FWCI
- 33.29
- Type
- journal article
- Language
- en
- Open access
- diamond
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.