The effect of user-controllable filters on the prediction of online hotel reviews

Product reviews have gained much popularity in recent years. This study examines the theoretical foundation of review helpfulness and reports how the interactions among three user-controllable filters together with three groups of predictors affect review helpfulness. Reviews from TripAdvisor.com were analyzed against three analytical models. The results show that these groups of variables have a varying effect on different user-controllable filters. Review rating and number of words are key predictors of helpfulness across all three filters. The recency, frequency, and monetary (RFM) model has received a consistent support across all filters as well. Managerial implications are provided.