Assessing Review Recommendation Techniques under a Ranking Perspective
Luciana B. Maroun, Mirella Moura Moro, Jussara Marques Almeida, Ana Paula C. Silva · 2016
Reading online reviews before a purchase is a customary action nowadays. Nevertheless, the increasing volume of reviews works as a barrier to their effectiveness so that many approaches try to predict reviews' quality, which is not standardized to all users due to different backgrounds and preferences. Thus, recommending reviews in a personalized fashion is probably more accurate. Here, we analyze methods for recommending reviews that have not been compared against each other yet. Our experiments consider parameter tuning and comparison through statistical tests. Such study allows to understand the state-of-the-art and to evidence potential improvement directions. Our results show that assessing under a ranking perspective, model simplicity and observed features are important traits for this problem, being Support Vector Regression the best solution.