The identification of Noteworthy Hotel Reviews for Hotel Management

The rapid emergence of user-generated content (UGC) inspires knowledge sharing among Internet users. A good example is the well-known travel site TripAdvisor.com, which enables users to share their experiences and express their opinions on attractions, accommodations, restaurants, etc. The UGC about travel provide precious information to the users as well as staff in travel industry. In particular, how to identify reviews that are noteworthy for hotel management is critical to the success of hotels in the competitive travel industry. We have employed two hotel managers to conduct an examination on Taiwan’s hotel reviews in Tripadvisor.com and found that noteworthy reviews can be characterized by their content features, sentiments, and review qualities. Through the experiments using tripadvisor.com data, we find that all three types of features are important in identifying noteworthy hotel reviews. Specifically, content features are shown to have the most impact, followed by sentiments and review qualities. With respect to the various methods for representing content features, LDA method achieves comparable performance to TF-IDF method with higher recall and much fewer features.