This study presents a data mining approach for modeling TripAdvisor score using 504 reviews published in 2015 for the 21 hotels located in the Strip, Las Vegas. Nineteen quantitative features characterizing the reviews, hotels and the users were prepared and used for feeding a support vector machine for modeling the score. The results achieved reveal the model demonstrated adequate predictive performance. Therefore, a sensitivity analysis was applied over the model for extracting useful knowledge translated into features' relevance for the score. The findings unveiled user features related to TripAdvisor membership experience play a key role in influencing the scores granted, clearly surpassing hotel features. Also, both seasonality and the day of the week were found to influence scores. Such knowledge may be helpful in directing efforts to answer online reviews in alignment with hotel strategies, by profiling the reviews according to the member and review date.

--

Customer feedback,Customer reviews,Online reviews,Knowledge extraction,Data mining,Modeling,Sensitivity analysis,Las Vegas

• Economics and Business - Social Sciences