Developing a Natural Language Processing Approach for Analyzing Student Ideas in Calculus-Based Introductory Physics
Date of Award
University Scholars Director
Dr. Christine Chaney
First Advisor/Committee Member
Lisa M. Goodhew
Second Advisor/Committee Member
Tor Ole B. Odden
natural language processing, physics education, latent dirichlet allocation, conceptual resources
Research characterizing common student ideas about particular physics topics has made a significant impact on university-level physics teaching by providing knowledge that supports instructors to target their instruction and by informing curriculum development. This work utilizes a Natural Language Processing algorithm (Latent Dirichlet Allocation, or LDA) to categorize student ideas, with the goal of significantly expediting the process of categorizing student ideas. We preliminarily test the LDA approach by applying the algorithm to a collection of introductory physics student responses to a conceptual question about circuits, specifically attending to whether it is useful for characterizing conceptual resources, or student ideas that may be fruitful for science learning. We find that for a large enough collection of student responses (N ≈ 500), LDA can be useful for characterizing student resources for conceptual physics questions. We discuss some considerations that researchers may take into account as they interpret the results of the LDA algorithm for characterizing student’s physics ideas.
Geiger, Jon M.; Goodhew, Lisa M.; and Odden, Tor Ole B., "Developing a Natural Language Processing Approach for Analyzing Student Ideas in Calculus-Based Introductory Physics" (2022). Honors Projects. 155.
Additional Rights Information
Copyright held by author.