EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An Analysis of ChatGPT-Generated Cloze Tests for Reading Assessment of College Students: Practicality, Validity, and Reliability

Muhammad Iqbal Julianda, Dinovia Fannil Kher

Journal of English Language Teaching · 10.03.2026 · 15 (1) · 27-34

DOI: 10.24036/jelt.v15i1.48 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of English Language Teaching, online erschienen am 10.03.2026. Verfasst von Muhammad Iqbal Julianda und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The use of artificial intelligence in language assessment has increased interest in automated test generation. In reading assessment, cloze tests are widely used to measure comprehension through contextual processing. This study examines the practicality, validity, and reliability of a ChatGPT-generated cloze test for reading assessment of college students. Using a descriptive quantitative design, 25 students completed a 30-item cloze test generated by ChatGPT without human modification. Practicality was measured through a 20-item student perception questionnaire, while validity and reliability were analyzed using corrected item–total correlation and Cronbach’s Alpha. The results indicate high practicality and acceptable reliability, although only a limited number of items were valid. These findings suggest that ChatGPT can support language test generation with proper statistical analysis.

Zitieren

APA

Julianda, M. I., & Kher, D. F. (2026). An Analysis of ChatGPT-Generated Cloze Tests for Reading Assessment of College Students: Practicality, Validity, and Reliability. Journal of English Language Teaching, 15(1), 27-34. https://doi.org/10.24036/jelt.v15i1.48

Vancouver

Julianda MI, Kher DF. An Analysis of ChatGPT-Generated Cloze Tests for Reading Assessment of College Students: Practicality, Validity, and Reliability. Journal of English Language Teaching. 2026;15(1):27-34. doi:10.24036/jelt.v15i1.48

BibTeX
@article{Julianda2026,
  author = {Julianda, Muhammad Iqbal and Kher, Dinovia Fannil},
  title = {An Analysis of ChatGPT-Generated Cloze Tests for Reading Assessment of College Students: Practicality, Validity, and Reliability},
  journal = {Journal of English Language Teaching},
  year = {2026},
  volume = {15},
  number = {1},
  pages = {27--34},
  doi = {10.24036/jelt.v15i1.48}
}
Kostenlos starten →