International Journal of Computer Science and Telecommunications
Social networking has become an intertwined part of the people daily lives, with these websites having a user base of several hundred million. Friend recommendation system is a crucial aspect of these social networking platforms, but it hasn't received the importance it deserves. A good recommendation system would not only give the platform a more intuitive look but it will also improve performance of entire architecture. The authors have proposed a system using neural network and diversified weights based on multilayer text extraction, frequency of communication for friend recommendation from friends of friends.