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

TL;DR

The paper tackles the challenge of improving EFL reading comprehension by personalizing materials to individual interests. It proposes an LLM-driven transcreation pipeline that tailors passages and questions from the RACE-C dataset through topic extraction, Bloom's taxonomy-based question analysis, and linguistic-feature preservation, with expert validation. In a controlled trial with Korean learners, personalized, interest-aligned passages improved overall comprehension and motivation retention, especially on higher-level analytical items, and shortened test turnaround time. The work demonstrates the practical potential of content transcreation for scalable, interest-aware English reading instruction and outlines future work on finer interest alignment and broader cultural-cognitive adaptation.

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.

Figures (2)

• Figure 1: Transcreated reading passage and question. A source data with the uninterested topic (right) is transcreated into the student's interested topic (left).
• Figure 2: Test score differences within Group A/B