2025 ASEE Annual Conference & Exposition

Designing and Testing AI-based Text Personalization Tools

Large Language Models (LLMs) offer unprecedented opportunities for individualized instruction by tailoring reading materials to students’ unique needs and preferences at scale. In this study, we introduce an LLM-powered personalization framework to adapt the complexity, format, and presentation of text-based educational content to students’ individual preferences. Our approach breaks personalization into a series of smaller tasks—describing learner preferences, rewriting texts, and evaluating accuracy—with the goal of enhancing accessibility and engagement. To rapidly refine prompts and system design, we simulate users by assigning multiple LLM agents the roles of both “student” and “teacher.” This closed-loop simulation allowed us to iterate swiftly on prompt engineering and platform features, enabling extensive testing and fine-tuning before deploying the framework with real students. Future work will therefore include classroom trials and human-subject evaluations to validate the impact of the achieved LLM-powered text personalization on student motivation and learning outcomes. By showcasing the feasibility of AI-driven customization, this paper points to new frontiers for delivering student-centered learning experiences in engineering education and beyond.

Authors

Mr. Michael Thomas Vaccaro Jr University of Connecticut [biography]

Michael Vaccaro is a fourth-year Ph.D. student in the School of Civil and Environmental Engineering at the University of Connecticut. He received his Bachelor of Science in Civil Engineering from the University of Connecticut in 2021. In addition to his work in structural engineering, Michael's interests in teaching and learning have inspired him to pursue interdisciplinary research spanning the fields of engineering, artificial intelligence, and neuroscience. His recent work in these areas has been supported by his major advisor's NSF MCA project and a transdisciplinary NSF Research Traineeship (TRANSCEND). Michael's engineering education research explores artificial intelligence's potential in K-12 science education, particularly in developing personalized learning environments.
Mikayla Friday University of Connecticut [biography]

Mikayla is a second-year PhD student studying Engineering Education at the University of Connecticut.
Dr. Zeynep Gonca Akdemir-Beveridge http://orcid.org/0000-0002-4352-239X University of Connecticut [biography]

Zeynep G. Akdemir-Beveridge is a Postdoctoral Research Associate at the University of Connecticut. Her current research focuses on exploring the creative productivity of engineering students and promoting strength-based approaches in engineering education to better support neurodiverse learning profiles in STEM/engineering learning environments. Her doctoral research centered on K–12 curriculum development specifically tailored to quantum information science and engineering, as well as student motivation and engagement in science education. A third area of her work involves the application of artificial intelligence (AI) in science and engineering education, particularly in the context of personalized learning. She is the recipient of the Best of Computers in Education award for her co-authored work presented at the 2022 ASEE Annual Conference & Exposition.
Prof. Arash Esmaili Zaghi P.E. http://orcid.org/0000-0003-2246-2911 University of Connecticut [biography]

Arash E. Zaghi is a Professor in the Department of Civil and Environmental Engineering at the University of Connecticut. He received his PhD in 2009 from the University of Nevada, Reno, and continued there as a Research Scientist. His latest

Note

The full paper will be available to logged in and registered conference attendees once the conference starts on June 22, 2025, and to all visitors after the conference ends on June 25, 2025

For those interested in:

Academia-Industry Connections
Broadening Participation in Engineering and Engineering Technology
computer science
engineering technology
Faculty