Revealing Customer Satisfaction with Hotels through Multi-Site Online Reviews: A Method Based on the Evidence Theory

Abstract

Hotel managers can learn about hotel customer satisfaction by analyzing online reviews. There are differences in the experience of reviewers, the release time and the degree of recognition for different online reviews, which leads to different reliability in reflecting customer satisfaction. The issue of how to determine hotel customer satisfaction more rationally with this reliability in mind is still a problem. To address this problem, this paper proposes a method for measuring hotel customer satisfaction based on the Dempster-Shafer (D-S) evidence theory, which considers the reliability of online reviews and information from multiple online travel review websites. This method is composed of three stages. First, considering the difference in online reviews' reliability, the basic probability assignment is generated based on online reviews. Next, the aggregation of the evaluation information is conducted based on the entropy weight method and Dempster's rule of combination. Finally, the utility function is used to calculate the expected utility, and customer satisfaction is analyzed based on the calculated expected utility. Therefore, improvement strategies of customer satisfaction can be developed according to customer satisfaction ranking. To verify the feasibility and effectiveness of this method, a case study for four hotels is presented. The proposed method is expected to help hotel managers understand the hotel's customer satisfaction, and develop corresponding improvement strategies to enhance its competitiveness.