Individual risk attitudes and expectations to support online hotel decisions: a UGC-driven intelligent decision-making approach

This paper proposes an adjustable intelligent decision-making method for online hotel booking platforms, aiming to reveal the differences in hotel selection results for different types of travelers. In this proposed method, first, considering the credibility of online reviews, text mining methods are used to measure the preferences of five types of travelers: business, couple, family, friends, and singles; Second, the risk attitudes of different types of traveler are discussed and a decision reliability level assessment model is constructed accordingly to the attribute preferences; Third, an adjustable TODIM method based on preferences and risk attitudes is proposed to determine the list of hotel selections for five types of travelers. Finally, the proposed method is validated by a case study involving 13 hotels, and its effectiveness is illustrated by comparative analysis. The results indicate that there are differences in risk attitudes and hotel selection results for travelers in different market segments.