Should we have a blind faith in the ChatGPT of generative AI in the tourism sector?

This study investigates the reliability of variables generated by ChatGPT in explaining resort tourists’ satisfaction, comparing them with variables validated through big data analysis and expert review. The results show that while most ChatGPT-derived variables had a significant impact on satisfaction, two variables – value and sustainability – were not statistically significant. In contrast, location, service quality, facilities, and experience programs consistently demonstrated strong effects. These findings suggest that while ChatGPT can be a valuable exploratory tool, its outputs should not be accepted uncritically, highlighting the importance of empirical validation and expert oversight in tourism research.