Can ChatGPT Perform a Grounded Theory Approach to Do Risk Analysis? An Empirical Study
Yaxian Zhou, Yufei Yuan, Kai Huang, Xiangpei Hu
Abstract
Grounded theory is a widely used scientific method for generating theories from qualitative data analysis. However, it is often time-consuming and requires professional training. Generative artificial intelligence, such as ChatGPT, excels in understanding and analyzing text, making it a valuable tool for qualitative research. This research proposes a novel approach to guide ChatGPT using the grounded theory method for qualitative data analysis and to design rigorous metrics for evaluating its performance. Using risk analysis as a case study, we compare ChatGPT’s results with those obtained through manual methods. Our findings show that, with expert guidance, ChatGPT can effectively perform the grounded theory method, achieving results comparable to those of human analysts. To maximize its potential, researchers should properly guide ChatGPT in performing required tasks, rigorously evaluate its outputs, and ensure high-quality results. This approach can significantly enhance the efficiency and quality of qualitative data analysis.