Natural Language Processing as a Scalable Method for Evaluating Educational Text Personalization by LLMs
Applied Sciences · 15.11.2025 · 15 (22) · 12128
DOI: 10.3390/app152212128 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 15.11.2025. Verfasst von Linh Huynh und 1 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 121 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Institute of Education Sciences, U.S. Department of Education.
Abstract (Originalsprache)
Four versions of science and history texts were tailored to diverse hypothetical reader profiles (high and low reading skills and domain knowledge), generated by four Large Language Models (i.e., Claude, Llama, ChatGPT, and Gemini). The Natural Language Processing (NLP) technique was applied to examine variations in Large Language Model (LLM) text personalization capabilities. NLP was leveraged to extract and quantify linguistic features of these texts, capturing linguistic variations as a function of LLMs, text genres, and reader profiles. An approach leveraging NLP-based analyses provides an automated and scalable solution for evaluating alignment between LLM-generated personalized texts and readers’ needs. Findings indicate that NLP offers a valid and generalizable means of tracking linguistic variation in personalized educational texts, supporting its use as an evaluation framework for text personalization.
Förderung
- Institute of Education Sciences, U.S. Department of Education
Zitieren
APA
Huynh, L., & McNamara, D. S. (2025). Natural Language Processing as a Scalable Method for Evaluating Educational Text Personalization by LLMs. Applied Sciences, 15(22), 12128. https://doi.org/10.3390/app152212128
Vancouver
Huynh L, McNamara DS. Natural Language Processing as a Scalable Method for Evaluating Educational Text Personalization by LLMs. Applied Sciences. 2025;15(22):12128. doi:10.3390/app152212128
BibTeX
@article{Huynh2025,
author = {Huynh, Linh and McNamara, Danielle S.},
title = {Natural Language Processing as a Scalable Method for Evaluating Educational Text Personalization by LLMs},
journal = {Applied Sciences},
year = {2025},
volume = {15},
number = {22},
pages = {12128},
doi = {10.3390/app152212128}
}
EUVIMED