Ranking Hotel Reviews Based on User's Aspects Importance and Opinions

Abstract

Online product reviews have become fundamental to users' purchasing decisions. Many websites provide rating-based ranking of entities, but analyzing the set of textual reviews is still time-consuming. Indeed, each user (reader) must build his/her own judgment from the set of reviews of the other users (writers), who might not have the same expectations and needs. To speed up this process, work have proposed more personalized rankings, which are restricted to the writer's perspective. In this work, we present an approach to rank reviews of an entity of interest, a hotel, based on the reader's profile. The method extracts a profile from free-text reviews and uses it to assess the degree of relevance of each review to rank according to the user's interests. The results obtained in the experiment exhibit a Mean Reciprocal Rank (MRR) of 0.72%, which is higher than comparable approaches of the literature. This paper also emphasizes the lack of available material to undertake such research, and sketches a methodology for evaluation.