Abstract: Nowadays, online social networks is a very popular communication platform, using on awide range of applications. Social networking sites employ recommendation systems in contribution to providing better user experiences. Existing social networking services recommend friends to users based on their social graphs, which may not be the most appropriate to reflecta user’s preferences on friend selection in real life.We propose, a novel semantic-based friend recommendation system for social networks,which recommends friends to users based on their life styles instead of social graphs. Novelsemantic approach measures the similarities of two members based on information containedin their profiles and recommends friends to users if their life styles have high similarity. Comparison Analysis Algorithm helps in securing the users data from visualizing to others. It alsohelp users to choose accurate friend requests by checking the matching percentage value.The results show that the recommendations accurately reflect the preferences of users inchoosing friends. This system can be used in finding accurate and secure recommendationsin social networks. Results of this system represent strong potential for developing link recommendation systems using this combined approach of personal interests and the underlyingnetwork.

Keywords: social networking services, friend recommendation, graphs, novel semantic, Comparison Analysis Algorithm.