Graduation Semester and Year
Summer 2025
Language
English
Document Type
Dissertation
Degree Name
Doctor of Philosophy in Physics and Applied Physics
Department
Physics
First Advisor
Ramon Lopez
Second Advisor
Zdzislaw Musielak
Third Advisor
Ann Cavallo
Fourth Advisor
Alexander Weiss
Fifth Advisor
James Alvarez
Abstract
Artificial intelligence (AI) is poised to transform science education, yet questions remain on how best to integrate these technologies into teaching and learning. This dissertation investigates the use of AI-driven tools in university physics courses through three complementary studies. In the first study, a generative language model (ChatGPT) was used to create novel physics homework problems aligned with course objectives. Analysis showed that, after expert vetting, AI-generated questions can foster higher-order problem-solving and reduce student reliance on solution memorization, though careful instructor oversight is required to ensure accuracy. The second study embedded an AI chatbot as a learning aid in an online physics course and applied Computational Grounded Theory to thousands of student–AI dialogues. This innovative method revealed patterns of student misconceptions (e.g. in quantum and relativistic physics) and demonstrated a scalable approach to analyzing student reasoning through AI-mediated interactions. The third study evaluated a custom AI-powered homework platform (aiPlato) in an introductory physics class, linking high student engagement with the system’s instant feedback and guidance to significantly improved exam performance and positive student feedback on learning experience. Across these investigations, the findings highlight that when thoughtfully integrated, AI can act as a pedagogical ally - generating tailored learning materials, illuminating students’ thought processes, and providing personalized support at scale. This work offers practical frameworks and evidence for combining AI technology with evidence-based teaching practices, and it outlines a future research agenda to explore students’ perceptions of AI in diverse educational settings. The implications extend to educators and researchers across disciplines, illustrating how AI-enhanced learning tools can advance both instructional effectiveness and the empirical study of how students learn in the age of AI.
Keywords
Physics education, Artifical intelligence, Educational technology, Intelligent tutoring systems, LLMs
Disciplines
Artificial Intelligence and Robotics | Computer Sciences | Curriculum and Instruction | Data Science | Education | Educational Assessment, Evaluation, and Research | Educational Technology | Graphics and Human Computer Interfaces | Higher Education | Numerical Analysis and Scientific Computing | Online and Distance Education | Other Computer Engineering | Other Computer Sciences | Other Education | Other Physics | Physics | Science and Mathematics Education
License
This work is licensed under a Creative Commons Attribution-Share Alike 4.0 International License.
Recommended Citation
Dange, Atharva, "Personalized Physics Learning through AI: Insights from Problem Generation, Chatbot Dialogues, and Intelligent Tutoring Systems" (2025). Physics Dissertations. 182.
https://mavmatrix.uta.edu/physics_dissertations/182
Included in
Artificial Intelligence and Robotics Commons, Curriculum and Instruction Commons, Data Science Commons, Educational Assessment, Evaluation, and Research Commons, Educational Technology Commons, Graphics and Human Computer Interfaces Commons, Higher Education Commons, Numerical Analysis and Scientific Computing Commons, Online and Distance Education Commons, Other Computer Engineering Commons, Other Computer Sciences Commons, Other Education Commons, Other Physics Commons, Science and Mathematics Education Commons