Opinion and Suggestion Analysis for Expert Recommendations

Abstract

In this paper, we propose the use of finegrained information such as opinions and suggestions extracted from users ’ reviews about products, in order to improve a recommendation system. While typical recommender systems compare a user profile with some reference characteristics to rate unseen items, they rarely make use of the content of reviews users have done on a given product. In this paper, we show how we applied an opinion extraction system to extract opinions but also suggestions from the content of the reviews, use the results to compare other products with the reviewed one, and eventually recommend a better product to the user. 1