Integration of Artificial Intelligence in Educational Measurement: Efficacy of ChatGPT in Data Generation within the Scope of Item Response Theory

TL;DR

This study evaluates ChatGPT 3.5's ability to generate data for Item Response Theory, finding it effective for IRT assumptions but less so for item parameter simulation, thus supporting its use in educational measurement research.

Contribution

It demonstrates ChatGPT 3.5's potential as a tool for developing IRT data generation algorithms, highlighting its strengths and limitations.

Findings

ChatGPT 3.5 effectively meets IRT assumptions.

Less effective in simulating item parameters.

Supports use of ChatGPT in educational measurement research.

Abstract

The aim of this study is to investigate the effectiveness of ChatGPT 3.5 in developing algorithms for data generation within the framework of Item Response Theory (IRT) using the R programming language. In this context, validity examinations were conducted on data sets generated according to the Two-Parameter Logistic Model (2PLM) with algorithms written by ChatGPT 3.5 and researchers. These examinations considered whether the data sets met the IRT assumptions and the simulation conditions of the item parameters. As a result, it was determined that while ChatGPT 3.5 was quite successful in generating data that met the IRT assumptions, it was less effective in meeting the simulation conditions of the item parameters compared to the algorithm developed by the researchers. In this regard, ChatGPT 3.5 is recommended as a useful tool that researchers can use in developing data generation algorithms for IRT.