Saved in:
Bibliographic Details
Main Author: Wang, Huanxiao
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.07451
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908641498497024
author Wang, Huanxiao
author_facet Wang, Huanxiao
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_07451
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Exploring the Psychometric Validity of AI-Generated Student Responses: A Study on Virtual Personas' Learning Motivation
Wang, Huanxiao
Computers and Society
Artificial Intelligence
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.
title Exploring the Psychometric Validity of AI-Generated Student Responses: A Study on Virtual Personas' Learning Motivation
topic Computers and Society
Artificial Intelligence
url https://arxiv.org/abs/2511.07451