METHODOLOGY FOR DESIGNING PEDAGOGICAL TEST ITEMS USING ARTIFICIAL INTELLIGENCE

Authors

  • Raisov Shamsiddin Rashid o‘g‘li Master’s student in Testology and Knowledge Assessment Department of Master’s Studies Termez State Pedagogical Institute, Uzbekistan Author
  • Ismailov Murodulla Kaxramonovich Doctor of Philosophy (PhD) in Pedagogical Sciences, Associate Professor Termez State Pedagogical Institute, Uzbekistan Author

Keywords:

Keywords: artificial intelligence, pedagogical testing, test item design, educational assessment, testology, generative AI, large language models, Bloom’s taxonomy, prompt engineering, validity, reliability, psychometric analysis.

Abstract

Abstract: This article examines the methodological foundations of designing pedagogical test items using artificial intelligence. The rapid development of generative artificial intelligence and large language models has created new opportunities for automating several stages of educational assessment, including the formulation of learning outcomes, preparation of test specifications, generation of test items and distractors, classification of questions according to cognitive levels, and preliminary quality control. However, artificial intelligence cannot independently guarantee the validity, reliability, fairness, and pedagogical appropriateness of a test. Therefore, the article proposes a human-centred methodology in which artificial intelligence functions as an auxiliary instrument under the continuous supervision of a teacher, subject-matter expert, and testologist. The proposed methodology includes the definition of the assessed construct, development of a test blueprint, preparation of verified source materials, prompt engineering, AI-assisted item generation, expert review, pilot administration, psychometric analysis, revision, and creation of an item bank.

References

1.American Educational Research Association, American Psychological Association, and National Council on Measurement in Education. (2014). Standards for Educational and Psychological Testing. Washington, DC: American Educational Research Association.

2.Anderson, L. W., and Krathwohl, D. R. (Eds.). (2001). A Taxonomy for Learning, Teaching, and Assessing: A Revision of Bloom’s Taxonomy of Educational Objectives. New York: Longman.

3.Bloom, B. S., Engelhart, M. D., Furst, E. J., Hill, W. H., and Krathwohl, D. R. (1956). Taxonomy of Educational Objectives: The Classification of Educational Goals. Handbook I: Cognitive Domain. New York: David McKay Company.

4.Downing, S. M., and Haladyna, T. M. (Eds.). (2006). Handbook of Test Development. Mahwah, NJ: Lawrence Erlbaum Associates.

5.Haladyna, T. M. (2004). Developing and Validating Multiple-Choice Test Items. Mahwah, NJ: Lawrence Erlbaum Associates.

Downloads

Published

2026-06-09