Deep learning model based on expectation-confirmation theory to predict customer satisfaction in hospitality service

Customer satisfaction is one of the most important measures in the hospitality industry. Therefore, several psychological and cognitive theories have been utilized to provide appropriate explanations of customer perception. Owing to recent rapid developments in artificial intelligence and big data, novel methodologies have presented to examine several psychological theories applied in the hospitality industry. Within this framework, this study combines deep learning techniques with the expectation-confirmation theory to elucidate customer satisfaction in hospitality services. Customer hotel review comments, hotel information, and images were employed to predict customer satisfaction with hotel service. The results show that the proposed fused model achieved an accuracy of 83.54%. In addition, the recall value that predicts dissatisfaction improved from 16.46–33.41%. Based on the findings of this study, both academic and managerial implications for the hospitality industry are presented.