Date
Publisher
arXiv
This study explores whether large language models (LLMs) can simulate valid student responses for educational measurement. Using GPT -4o, 2000 virtual student personas were generated. Each persona completed the Academic Motivation Scale (AMS). Factor analyses(EFA and CFA) and clustering showed GPT -4o reproduced the AMS structure and distinct motivational subgroups.
Study at a glance
- Question: Can artificial intelligence accurately simulate student responses to a learning motivation survey?
- Setting and data: 2,000 virtual student personas generated by GPT-4o responding to the Academic Motivation Scale.
- Method: Factor analysis (EFA and CFA) and clustering of simulated survey responses.
Why it matters
Whether large language models can simulate valid student responses for educational measurement remains an open question. Specifically, the psychometric validity of virtual personas' learning motivation requires exploration.
Key findings
- Across 2,000 simulated student personas, an AI tool reproduced the established structure of a standard academic motivation survey.
- The AI-generated personas reflected distinct subgroups of student motivation.
- Generative AI simulated valid response patterns for educational motivation measurement.
Summary drafted with AI from the paper’s abstract 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
