A Fuzzy Community-Based Recommender System Using PageRank
This work addresses the need for more accurate recommender systems for user service providers, though it appears incremental as it builds on existing community-based and PageRank approaches.
The paper tackled the problem of improving recommendation systems by introducing a fuzzy community detection method using personalized PageRank, which leverages local and global user similarities. The results show that this method outperforms recent recommender systems on MovieLens and FilmTrust datasets.
Recommendation systems are widely used by different user service providers specially those who have interactions with the large community of users. This paper introduces a recommender system based on community detection. The recommendation is provided using the local and global similarities between users. The local information is obtained from communities, and the global ones are based on the ratings. Here, a new fuzzy community detection using the personalized PageRank metaphor is introduced. The fuzzy membership values of the users to the communities are utilized to define a similarity measure. The method is evaluated by using two well-known datasets: MovieLens and FilmTrust. The results show that our method outperforms recent recommender systems.