Enhancing Japanese EFL Students’ Grammar Accuracy and Writing Fluency Using ChatGPT: A Mixed-Method Study

Authors

  • Rosbe Colina

    Osaka City Board of Education, Osaka 530-8201, Japan
  • Dominic Bryan San Jose

    Recoletos de Bacolod Graduate School, University of Negros Occidental-Recoletos, Bacolod 6100, Philippines
  • Mike Lawrence Ratunil

    Ritsumeikan Uji Junior and Senior High School, Uji 611-0031, Japan

DOI:

https://doi.org/10.30564/jiep.v8i2.12789
Received: 15 September 2025 | Revised: 3 November 2025 | Accepted: 11 November 2025 | Published Online: 18 November 2025

Abstract

This mixed-methods study investigated whether or not ChatGPT worked as a writing aid to increase the grammar accuracy and writing fluency of Japanese EFL students. Thirty Japanese senior high school students took part in a six-week intervention that included ChatGPT in process-based writing assignments. Three research questions were examined in the study: (1) How much does ChatGPT help learners become more accurate with grammar? (2) What impact does ChatGPT have on writing fluency? (3) What role does ChatGPT play in the development of students' writing? Pre- and post-tests evaluated using analytical rubrics yielded quantitative data. Grammar accuracy (t(29) = 8.62, p < 0.001, d = 1.11) and writing fluency (t(29) = 6.46, p < 0.001, d = 0.84) both significantly improved, according to paired-samples t-tests. Three main themes emerged from qualitative data from learner journals, semi-structured interviews, and classroom observations: ChatGPT as a grammar mentor, fluency development via iterative rewriting, and growing concerns about overreliance. Students reported better coherence and flow in written texts, increased awareness of frequent grammatical errors, and increased confidence in editing sentences. Results show that when ChatGPT is used as a scaffolded, process-oriented tool rather than as a replacement for independent writing, it can support both linguistic accuracy and fluency. Students' worries about dependence, however, emphasize the necessity of clear instruction in digital literacy. The study offers pedagogical implications for integrating AI responsibly in Japanese and wider Asian EFL contexts and adds empirical evidence to the expanding body of research on AI-assisted EFL writing.

Keywords:

ChatGPT; EFL Writing; Grammar Accuracy; Writing Fluency; Japanese Learners; Mixed-Methods Research; AI-Assisted Language Learning

References

[1] Amoush, K.H., Alhosban, A.A., 2025. Mastering EFL Writing With ChatGPT: A Systematic Review of Benefits, Challenges, and Best Practices. Theory and Practice in Language Studies. 15(8), 2576–2583. DOI: https://doi.org/10.17507/tpls.1508.14

[2] Xiao, F., Zhu, S., Xin, W., 2025. Exploring the Landscape of Generative AI (ChatGPT)-Powered Writing Instruction in English as a Foreign Language Education: A Scoping Review. ECNU Review of Education. 8(1), 1–19. DOI: https://doi.org/10.1177/20965311241310881

[3] Kim, P.W., 2025. Fog Computing for Artificial Intelligence Digital Textbooks: Educational Scaffolding and Security and Privacy Challenges. Expert Systems. 42(2), e13801. DOI: https://doi.org/10.1111/exsy.13801

[4] Luo, Q.Z., Hsiao-Chin, L.Y., 2023. The Influence of AI-Powered Adaptive Learning Platforms on Student Performance in Chinese Classrooms. Journal of Education. 6(3), 1–12. DOI: https://doi.org/10.53819/81018102t4181

[5] Quyet, C.B., Minh, N.B., Anh, N.P., 2024. Using Artificial Intelligence Tool in Studying English Skills in Vietnam: An Experimental Research for Vietnamese High School Students. Journal of Ecohumanism. 3(6), 1883–1894.

[6] Fujio, M., 2024. New Opportunities for Japanese Universities to Internationalize Communication Courses. Journal of Technical Writing and Communication. 54(2), 163–180. DOI: https://doi.org/10.1177/00472816231188110

[7] Hiramoto, M., 2023. The Monolingual Borrowers: Reconciling the Success and Failure of English in Japan. Asian Englishes. 25(1), 81–94. DOI: https://doi.org/10.1080/13488678.2022.2034258

[8] Weinmann, M., Kanaizumi, R., Arber, R., 2021. English Language Education Reform in Pre-2020 Olympic Japan: Educator Perspectives on Pedagogical Change. International Journal of the Sociology of Language. 2021(271), 107–131. DOI: https://doi.org/10.1515/ijsl-2020-0035

[9] Fu, M., Li, S., 2022. The Effects of Immediate and Delayed Corrective Feedback on L2 Development. Studies in Second Language Acquisition. 44(1), 2–34. DOI: https://doi.org/10.1017/S0272263120000388

[10] Zhang, Z., Huang, X., 2024. The Impact of Chatbots Based on Large Language Models on Second Language Vocabulary Acquisition. Heliyon. 10(3), e25370. DOI: https://doi.org/10.1016/j.heliyon.2024.e25370

[11] Rassaei, E., Ravand, H., 2024. Immediate Versus Delayed Prompts, Field Dependence and Independence Cognitive Style, and L2 Development. International Review of Applied Linguistics in Language Teaching. 62(2), 927–952. DOI: https://doi.org/10.1515/iral-2022-0137

[12] Seo, J.-Y., 2024. Exploring the Educational Potential of ChatGPT: AI-Assisted Narrative Writing for EFL College Students. Language Teaching Research Quarterly. 43, 1–21.

[13] Sharshova, R., Salkhanova, Z., Maral, A., 2025. The Use of AI Writing Tools in Second Language Learning to Enhance Kazakh IT Students’ Academic Writing Skills. Forum for Linguistic Studies. 7(8), 251–267. DOI: https://doi.org/10.30564/fls.v7i8.10408

[14] Egitim, S., 2022. Do Japanese students lack critical thinking? Addressing the misconception. Power and Education. 14(3), 304–309. DOI: https://doi.org/10.1177/17577438221107203

[15] Lu, J., Sato, R., 2025. Linguistic dimensions of comprehensibility and perceived fluency in L2 speech across tasks of varying complexity. Journal of Second Language Pronunciation. 11(2), 240–266. DOI: https://doi.org/10.1075/jslp.24057.lu

[16] Kasai, C., Sumiya, M., Koike, T., et al., 2022. Neural underpinning of Japanese particle processing in non-native speakers. Scientific Reports. 12(1), 18740. DOI: https://doi.org/10.1038/s41598-022-23382-8

[17] Muroya, A., 2022. A bidirectional comparison of English and Japanese learners' willingness to communicate in their foreign language. Ampersand. 9, 100081. DOI: https://doi.org/10.1016/j.amper.2021.100081

[18] Vygotsky, L., Cole, M., 2018. Lev Vygotsky: Learning and Social Constructivism. In Learning Theories for Early Years Practice. SAGE Publications: London, UK. pp. 68–73.

[19] Abbuhl, R., 2022. Interactionist Approach to Corrective Feedback. In: Mohebbi, H., Coombe, C. (Eds.). Research Questions in Language Education and Applied Linguistics: A Reference Guide. Springer International Publishing: Cham, Switzerland. pp. 103–106. DOI: https://doi.org/10.1007/978-3-030-79143-8_19

[20] Creswell, J.W., Poth, C.N., 2016. Qualitative Inquiry and Research Design: Choosing Among Five Approaches, 4th ed. SAGE Publications: Thousand Oaks, CA, USA.

[21] Buckley, R., 2022. Ten Steps for Specifying Saturation in Qualitative Research. Social Science and Medicine. 309, 115217. DOI: https://doi.org/10.1016/j.socscimed.2022.115217

[22] Byrne, D., 2022. A Worked Example of Braun and Clarke’s Approach to Reflexive Thematic Analysis. Quality and Quantity. 56(3), 1391–1412. DOI: https://doi.org/10.1007/s11135-021-01182-y

[23] Thomson, G., Crowther, S., 2022. Attuning to Trustworthiness and Final Reflections. In Hermeneutic Phenomenology in Health and Social Care Research. Routledge: London, UK. pp. 213–227.

[24] Sadeghi, K., Esmaeeli, M., 2024. Probing into Non-Native Learners’ Written Accuracy: Does Feedback Type Matter?. RELC Journal. 55(2), 422–437. DOI: https://doi.org/10.1177/00336882221092795

[25] Schenck, A., 2020. Using Meta-Analysis of Technique and Timing to Optimize Corrective Feedback for Specific Grammatical Features. Asian-Pacific Journal of Second and Foreign Language Education. 5(1), 16. DOI: https://doi.org/10.1186/s40862-020-00097-9

[26] Jang, S.S., 2020. The Efficacy of Different Types of Metalinguistic Information in L2 Written Corrective Feedback. English Teaching. 75(4), 33–56. DOI: https://doi.org/10.15858/engtea.75.4.202012.33

[27] Long, R.W., Watanabe, H., 2023. Teacher Recommendations for Writing Programs in Japanese Universities. International Journal of Information and Education Technology. 13(4), 650–657. DOI: https://doi.org/10.18178/ijiet.2023.13.4.1849

[28] Hibino, A., Matruglio, E., 2024. Reading to Learn for Learning to Write: Japanese EFL Teachers’ Perceptions About Reading to Learn. Indonesian Journal of Applied Linguistics. 14(1), 1–11. DOI: https://doi.org/10.17509/ijal.v14i1.70348

[29] Li, X., Li, B., Cho, S.J., 2023. Empowering Chinese Language Learners from Low-Income Families to Improve Their Chinese Writing With ChatGPT’s Assistance Afterschool. Languages. 8(4), 238. DOI: https://doi.org/10.3390/languages8040238

[30] Herman, J., Lara-Steidel, H., 2025. Artificial Intelligence on Campus: Revisiting Understanding as an Aim of Higher Education. Educational Theory. 75(4), 603–625. DOI: https://doi.org/10.1111/edth.70026

[31] Francis, N.J., Jones, S., Smith, D.P., 2025. Generative AI in Higher Education: Balancing Innovation and Integrity. British Journal of Biomedical Science. 81, 14048. DOI: https://doi.org/10.3389/bjbs.2024.14048

[32] Zhang, S., Zhao, X., Zhou, T., et al., 2024. Do You Have AI Dependency? The Roles of Academic Self-Efficacy, Academic Stress, and Performance Expectations on Problematic AI Usage Behavior. International Journal of Educational Technology in Higher Education. 21(1), 34. DOI: https://doi.org/10.1186/s41239-024-00467-0

[33] Surtees, V., Duff, P., 2022. Sociocultural Approaches to Speaking in Second Language Acquisition. In: The Routledge Handbook of Second Language Acquisition and Speaking. Routledge: New York, NY, USA. pp. 54–67.

Downloads

How to Cite

Colina, R., San Jose, D. B., & Ratunil, M. L. (2025). Enhancing Japanese EFL Students’ Grammar Accuracy and Writing Fluency Using ChatGPT: A Mixed-Method Study. Journal of International Education and Practice, 8(2), 103–117. https://doi.org/10.30564/jiep.v8i2.12789

Issue

Vol. 8 , Iss. 2 (December 2025): In Progress

Article Type

ARTICLE

License

Copyright © 2025 Rosbe Colina, Dominic Bryan San Jose, Mike Lawrence Ratunil

Creative Commons License

This is an open access article under the Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) License.