A Semantic-Based Friend Recommendation System Based On Lifestyle Matching release_ugh7u75tnzfw7l7h5ucwtmsozy

Abstract

Most of the social networking systems or friend recommendation systems used nowadays recommend friends based on their social connectivity or on a mutual basis. But this is a syntactic approach as there is no metric used and so it may not be that appropriate approach for friend recommendation. In this paper, a semantic-based friend recommendation system is proposed which recommends friends to users based on their lifestyles. Similarity of lifestyles between users is measured by a similarity metric and the system recommends those friends to the users that share high similarity among their lifestyles. Impact of user is calculated and a friend-matching graph is generated accordingly. Finally, the system returns a list of users with highest recommendation scores to the user. The system also includes a feedback mechanism which allows users to rate the friend recommendation.
In text/plain format

Archived Files and Locations