One-Topic-Doesn't-Fit-All: Transcreating Reading Comprehension Test for Personalized Learning

2025-11-12

AI Summary

Generic reading materials in EFL instruction often neglect learner interests, resulting in low engagement and motivation. Method: This study proposes a content transcreation framework integrating interest alignment with Bloom’s Taxonomy to simultaneously achieve semantic personalization and controlled linguistic difficulty. Leveraging GPT-4o, the framework processes the RACE-C dataset to identify topics, annotate cognitive levels, analyze linguistic features, and perform targeted rewriting—automatically generating interest-adapted reading texts and comprehension questions. Contribution/Results: It is the first work to jointly embed individual interest modeling and an educational taxonomy into an AI-driven content generation pipeline. A controlled empirical study with Korean EFL learners demonstrated that students using system-generated materials significantly outperformed controls in both reading comprehension scores and motivation maintenance (p < 0.01), confirming that interest-driven, cognitively structured transcreation enhances language learning efficacy.

Technology Category

• Natural Language Processing: Generation
• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Cognitive Modeling & Cognitive Systems: Computational Creativity

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Personalized learning has gained attention in English as a Foreign Language (EFL) education, where engagement and motivation play crucial roles in reading comprehension. We propose a novel approach to generating personalized English reading comprehension tests tailored to students'interests. We develop a structured content transcreation pipeline using OpenAI's gpt-4o, where we start with the RACE-C dataset, and generate new passages and multiple-choice reading comprehension questions that are linguistically similar to the original passages but semantically aligned with individual learners'interests. Our methodology integrates topic extraction, question classification based on Bloom's taxonomy, linguistic feature analysis, and content transcreation to enhance student engagement. We conduct a controlled experiment with EFL learners in South Korea to examine the impact of interest-aligned reading materials on comprehension and motivation. Our results show students learning with personalized reading passages demonstrate improved comprehension and motivation retention compared to those learning with non-personalized materials.

Problem

• Generating personalized reading comprehension tests for EFL students
• Transcreating passages aligned with individual learners' interests
• Enhancing student engagement and motivation in reading comprehension

Innovation

• Generating personalized reading comprehension tests using GPT-4
• Transcreating passages and questions aligned with student interests
• Integrating topic extraction and Bloom's taxonomy classification