AI-Generated Reading Comprehension Questions: a Comparative Analysis Through Bloom’s and Barrett’s Taxonomies

Keywords:
Reading Comprehension, Bloom's Taxonomy, Barrett’s Taxonomy, AI In Education, Literary Text Analysis

Abstract:
This paper explores the possibilities offered by recent AI models in creating reading comprehension questions. One of the most popular large language models (LLMs), ChatGPT–5.3, was used to generate 15 questions about two short stories, one in Serbian (Sve će to narod pozlatiti by Laza Lazarević) and one in English (The Lottery by Shirley Jackson). The items were generated for each text using the same prompt in different languages, and subsequently they were analysed through Bloom’s revised taxonomy and Barrett’s taxonomy of reading comprehension. The findings indicate a predominance of higher-order thinking questions, particularly analysis and evaluation levels, according to Bloom’s taxonomy, and inferential comprehension according to Barrett’s levels. Both sets of questions show more focus on critical thinking than on simple retrieval of information. One limitation is the lack of tasks at the creative level, indicating that AI-generated questions do not foster productive or generative students’ responses. This study suggests that AI has clear potential in language and literature teaching, but also important limitations. It can be concluded that large language models can help teachers by creating useful and intellectually engaging materials, but the materials and tasks produced should not be used without careful review. Teachers still play the most important role in adapting such materials to cover different thinking levels. Overall, these findings are an addition to the current research on AI in education, and they highlight the importance of well-designed prompts in preparing high-quality instructional content.

CITATION:

IEEE format

Copy to clipboard

A. Tripković, S. Čorboloković, “AI-Generated Reading Comprehension Questions: a Comparative Analysis Through Bloom’s and Barrett’s Taxonomies,” in Sinteza 2026 - International Scientific Conference on Information Technology, Computer Science, and Data Science, Belgrade, Singidunum University, Serbia, 2026, pp. 464-470. doi:10.15308/Sinteza-2026-464-470

APA format

Copy to clipboard

Tripković, A., Čorboloković, S. (2026). AI-Generated Reading Comprehension Questions: a Comparative Analysis Through Bloom’s and Barrett’s Taxonomies. Paper presented at Sinteza 2026 - International Scientific Conference on Information Technology, Computer Science, and Data Science. doi:10.15308/Sinteza-2026-464-470

BibTeX format
Download

RefWorks Tagged format
Download