Incorporating User Reviews as Implicit Feedback for Improving Recommender Systems

Recommendation systems have become extremely common in recent years due to the ubiquity of information across various applications. Online entertainment (e.g., Netflix), E-commerce (e.g., Amazon, Ebay) and publishing services such as Google News are all examples of services which use recommender systems. Recommendation systems are rapidly evolving in these years, but these methods have fallen short in coping with several emerging trends such as likes or votes on reviews. In this paper we have proposed a new method based on collaborative filtering by considering other users´ feedback on each review. To validate our approach we have compared our method with several known methods on Yelp data set. Our algorithm outperforms other approaches in terms of accuracy by as much as 9.5%. We also present our results using comparative analysis for particular categories of users and items. Our algorithm has promising results when handling several difficult user and item categories.