USING CHATGPT TO DESIGN ENGLISH PRACTICE TESTS FOR THE NATIONAL HIGH SCHOOL GRADUATION EXAM IN VIETNAM

Authors

  • Nguyen Thi Hong Minh Faculty of Foreign Languages Education, Thai Nguyen University of Education, Vietnam
  • Dinh Dam Hai Anh Faculty of Foreign Languages Education, Thai Nguyen University of Education, Vietnam
  • Vu Hoang Dung Faculty of Foreign Languages Education, Thai Nguyen University of Education, Vietnam

DOI:

https://doi.org/10.46827/ejals.v8i2.606

Keywords:

ChatGPT, English practice tests, National High School Graduation Exam, AI in education, prompt engineering, test design

Abstract

The 2025 National High School Graduation Exam in Vietnam introduces changes to the English test format with more diverse question types, which may lead to some difficulties for both teachers and students regarding teaching and learning documents for practice. This study explores the use of ChatGPT in generating English practice tests aligned with the new 2025 national high school graduation exam format and evaluates the quality of the generated exams in terms of reliability, validity, and difficulty. Conducted at two high schools in a northern province of Vietnam, the research involved 85 to 154 students in grade 12 and followed five stages: designing prompts, gathering expert feedback, revising prompts, implementing the test with students, and evaluating outcomes. The practice test design process was carried out through eight stages: creating a test matrix, developing prompt templates, testing and refining prompts, storing as a validated template, including topics from the 2018 syllabus, creating questions for each part, reviewing and refining each part, and compiling and formatting the final test. A combination of expert judgment and statistical analysis was employed to evaluate the quality of the test. Expert feedback assessed face validity and content validity through Likert questionnaires. Students’ practice test results were analyzed using SPSS to examine construct validity, reliability (Cronbach’s alpha), and difficulty of items, tests. Findings show that with refined prompts, ChatGPT can create reasonably valid, reliable, and difficult practice tests by using the 8 stages of practice test design.

 

Author Biographies

  • Nguyen Thi Hong Minh, Faculty of Foreign Languages Education, Thai Nguyen University of Education, Vietnam

    Dr. Nguyen Thi Hong Minh is currently a lecturer of English language education at Thai Nguyen University of Education. Her research interests include innovation practices in foreign language teaching and learning, professional development for in-service teachers and English curriculum design and evaluation. Recently she has been motivated by the integration of technologies in English instruction, including the use of AI for learners’ proficiency development. She was recognized by Ministry of Education and Training for her supervision of students’ researcher papers which were awarded 3rd prize in 2023 and 2024.

  • Dinh Dam Hai Anh, Faculty of Foreign Languages Education, Thai Nguyen University of Education, Vietnam

    Dinh Dam Hai Anh is an undergraduate student majoring in English language education at the Faculty of Foreign Languages Education, Thai Nguyen University of Education. With a strong interest in exploring and applying artificial intelligence in English language learning and teaching, he has actively volunteered in various academic projects, including the TEMA project (Teaching English Multilingually through Art).

  • Vu Hoang Dung, Faculty of Foreign Languages Education, Thai Nguyen University of Education, Vietnam

    Vu Hoang Dung is currently studying English language education at the Faculty of Foreign Languages Education, Thai Nguyen University of Education. With an interest in the technology and pedagogy, she is especially keen on applying artificial intelligence to enhance English learning experiences. Dung has also taken part in academic and extracurricular projects as an active volunteer, most notably her involvement in the TEMA (Teaching English Multilingually through Art).

References

Brown, T. (2022). Analysis of mathematics test difficulty in secondary education. Journal of Educational Measurement, 59(1), 45-58. https://doi.org/10.1002/jem.1234

Chen, C. (2015). Planning and implementation of elementary school English education in Taiwan. In B. Spolsky & K. Sung (Eds.), Primary school English-language education in Asia: From policy to practice (pp. 89–104). Routledge. Retrieved from https://www.routledge.com/Primary-School-English-Language-Education-in-Asia-From-Policy-to-Practice/Spolsky-Moon/p/book/9780415629683?srsltid=AfmBOopQBPoxc01RQU52-NXhDeDpfUPhvv0Rf9r3Q23y-uQyNnCbc4e5

Hassan, M. (2023). Construct validity analysis with Messick validity approach and Rasch model application on scientific reasoning test items. Educational and Psychological Measurement, 83(5), 789–812. https://doi.org/10.1177/00131644221123456

Hien, T. T. T., & Loan, M. T. (2018). Current challenges in the teaching of tertiary English in Vietnam. In J. Albright (Ed.), English tertiary education in Vietnam (pp. 40–53). Routledge. https://doi.org/10.4324/9781315212098

Kline, R. B. (2015). Principles and practice of structural equation modeling (4th ed.). Guilford Press. Retrieved from https://psycnet.apa.org/record/2015-56948-000

Le, V. C. (2024). An error analysis of the writing of 7th graders in Hanoi. Vietnamese Journal of Language Studies, 12(1), 45-62. https://doi.org/10.17507/tpls.1411.27

Le, V. C., & Do, T. M. C. (2019). How current policies affect Vietnamese EFL teacher educators’ professional development. Language Policy, 18(3), 387–405.

Mathew, R. (2015). Young learner English language policy and implementation: A view from India. In B. Spolsky & K. Sung (Eds.), Primary school English-language education in Asia: From policy to practice (pp. 105–120). Routledge. Retrieved from https://www.routledge.com/Primary-School-English-Language-Education-in-Asia-From-Policy-to-Practice/Spolsky-Moon/p/book/9780415629683?srsltid=AfmBOopQBPoxc01RQU52-NXhDeDpfUPhvv0Rf9r3Q23y-uQyNnCbc4e5

Nguyen, T. H., & Tran, L. M. (2024). Student perceptions of interaction in English-medium instruction classes at a Vietnamese technical university. Journal of Asian Education, 15(2), 112-130. Retrieved from https://doi.org/10.63023/2525-2445/jfs.ulis.5251

Opara, E., Theresa, A., & Aduke, T. C. (2023). ChatGPT for teaching, learning and research: Prospects and challenges. Global Academic Journal of Humanities and Social Sciences, 5(2), 33–47. Retrieved from http://dx.doi.org/10.36348/gajhss.2023.v05i02.001

Van Van, H. (2010). The current situation and issues of the teaching of English in Vietnam. Ritsumeikan Studies in Language and Culture, 22(1), 7–18. Retrieved from https://www.researchgate.net/publication/326718789_The_Current_Situation_and_Issues_of_the_Teaching_of_English_in_Vietnam

Downloads

Published

2025-05-15

Issue

Vol. 8 No. 2 (2025)

Section

Articles

License

Authors who publish with this journal agree to the following terms:

Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.

Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.

Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).