PERC 2025 Abstract Detail Page
Previous Page | New Search | Browse All
| Abstract Title: | Exploring Query-Driven Centroiding and Embedding Strategies for Automated Thematic Analysis in Physics Education |
|---|---|
| Abstract Type: | Contributed Poster Presentation |
| Abstract: | Understanding how Physics Education Research (PER) has changed and matured helps researchers and materially improve physics teaching and learning. The advent of large language models (LLMs) and embedding-based NLP techniques opens new avenues for this work by enabling the analysis of large corpora with minimal manual coding. We explore the use of text embeddings and retrieval-augmented generation (RAG)-like methods without generative AI to analyze themes across a random sample of 94 articles from major PER journals. Specifically, we examine how two methodological choices affect topic modeling accuracy: (1) representing articles using a single embedding versus multiple sentence-level embeddings, and (2) deriving topic centroids from representative texts versus researcher-defined queries. All results are evaluated against a human-coded dataset focused on four overarching thematic categories: teacher-centered, student-centered, physics content, and journal business. Our findings inform best practices for researchers seeking scalable, interpretable, and low-barrier approaches to literature analysis in PER. |
| Session Time: | Poster Session A |
| Poster Number: | A-9 |
| Contributed Paper Record: | Contributed Paper Information |
| Contributed Paper Download: | Download Contributed Paper |
Author/Organizer Information | |
| Primary Contact: |
Michael Mingyar Montana State University Bozeman, MT 59715 Phone: 8149324710 |
| Co-Author(s) and Co-Presenter(s) |
Tor Ole B. Odden, Center for Computing in Science Education, Department of Physics, University of Oslo, 0316 Oslo, Norway Shannon Willoughby, Department of Physics, Montana State University, Bozeman, MT 59717 |
Contributed Poster | |
| Contributed Poster: | Download the Contributed Poster |
