Got It! Prompting Readability Using ChatGPT to Enhance Academic Texts for Diverse Learning NeedsShow others and affiliations
2025 (English)In: 15th International Conference on Learning Analytics and Knowledge, LAK 2025, Association for Computing Machinery (ACM) , 2025, p. 115-125Conference paper, Published paper (Refereed)
Abstract [en]
Reading skills are crucial for students' success in education and beyond. However, reading proficiency among K-12 students has been declining globally, including in Sweden, leaving many underprepared for post-secondary education. Additionally, an increasing number of students have reading disorders, such as dyslexia, which require support. Generative artificial intelligence (genAI) technologies, like ChatGPT, may offer new opportunities to improve reading practices by enhancing the readability of educational texts. This study investigates whether ChatGPT-4 can simplify academic texts and which prompting strategies are most effective. We tasked ChatGPT to re-write 136 academic texts using four prompting approaches: Standard, Meta, Roleplay, and Chain-of-Thought. All four approaches improved text readability, with Meta performing the best overall and the Standard prompt sometimes creating texts that were less readable than the original. This study found variability in the simplified texts, suggesting that different strategies should be used based on the specific needs of individual learners. Overall, the findings highlight the potential of genAI tools, like ChatGPT, to improve the accessibility of academic texts, offering valuable support for students with reading difficulties and promoting more equitable learning opportunities.
Place, publisher, year, edition, pages
Association for Computing Machinery (ACM) , 2025. p. 115-125
Keywords [en]
Analytics, Equity, Large language models, Literacy, Prompt engineering, Readability
National Category
Pedagogy Natural Language Processing
Identifiers
URN: urn:nbn:se:kth:diva-361966DOI: 10.1145/3706468.3706483Scopus ID: 2-s2.0-105000372142OAI: oai:DiVA.org:kth-361966DiVA, id: diva2:1949639
Conference
15th International Conference on Learning Analytics and Knowledge, LAK 2025, Dublin, Ireland, March 3-7, 2025
Note
Part of ISBN 9798400707018
QC 20250403
2025-04-032025-04-032025-04-03Bibliographically approved