Friend Recommendation System Based Semantic

Computer Engineering

In Existing social networking services recommend friends to users based on their social graphs, which is not appropriate to reflect a user’s preferences on friend selection in real life. We present a semantic-based friend recommendation system for social networks in which friends are recommended to user according to their life styles instead of social graphs. By using friend matching graph algorithm, a friend matching graph is being generated which shows/measures similarity of life styles between users, and recommends friends to users if their life styles have high similarity. By using text mining, we track user’s daily life as activity documents, from which his/her life styles are extracted by using the Latent Dirichlet Allocation algorithm. We also propose a similarity metric to measure the similarity of life styles between users, and rank the user based on their friend life style high similarity friend matching graph. After receiving a request, Friend recommendation system returns a list of people with highest recommendation scores to the query user. Finally, Friend Recommendation System integrates a feedback mechanism to further improve the recommendation accuracy.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.