Date
Publisher
arXiv
This study investigates the impact of a novel application of generative
artificial intelligence (AI) in physics instruction: engaging students in
prompting, refining, and validating AI-constructed simulations of physical
phenomena. In a second-semester physics course for life science majors, we
conducted a comparative study of three instructional approaches in a laboratory
focused on electric potentials: (i) students using physical equipment, (ii)
students using a prebuilt simulator, and (iii) students using AI to generate a
simulation. We found significant group differences in performance on conceptual
assessments of the laboratory content ({\eta}^2 = 0.359). Post-hoc analysis
showed that students in both the AI-generated and prebuilt simulation
conditions scored significantly higher on the conceptual assessments than
students in the physical equipment condition. Students in these groups also
reported more favorable perceptions of the learning experience. Finally, this
preliminary study highlights opportunities for developing students' modeling
skills through the processes of designing, refining, and validating
AI-generated simulations.
Study at a glance
- Question: How does student-guided AI simulation design affect conceptual physics understanding and attitudes compared to prebuilt simulations or physical labs?
- Setting and data: Introductory physics course for life sciences at a public R1 university in the western US, spring 2025, 187 students.
- Method: Comparative study with three quasi-experimental groups comparing post-lab conceptual tests, exams, and surveys using nonparametric tests.
Why it matters
Generative AI is transforming educational practices, but physics educators face wide variations in use and need research-validated approaches to effectively integrate AI for learning and scientific modeling.
Key findings
- Students in both the AI-generated and prebuilt simulation groups scored significantly higher on post-lab conceptual assessments than students using physical equipment.
- No significant differences in physics conceptual performance were found between the AI-generated and prebuilt simulation groups, or across groups on later midterm and final exams.
- Students in both simulation conditions reported significantly more positive attitudes toward the lab experience than students who used physical equipment.
Summary drafted with AI from the full paper and may contain errors. See the full paper for details.
What is the application?
Who is the user?
Who age?
Why use AI?
Study design
