Social bookmarking, Friend Recommendation, Behavioral data mining, Novelty, Serendipity, User behavior
Social media systems are becoming more and more popular now days. The amount of content shared in these system increases fast, leading users to face the well known Social interaction overload problem arises. In order to overcome this problem, Social Recommendation systems have been designed & developed. In order to filter content and recommend to users only interesting items. A form of social media, known as social bookmarking systems allows sharing bookmarks in social network. A user adds as a friend or follows another user and receives updates on the bookmarks added by that user. In Social Recommendation one problem arises of over Specialization problem. Which is related to recommendation that are too similar to the items already consider by the users. This paper presents an analysis of the state of art on user recommendation in social environments, in order to derive a design and architecture of a friend recommendation system in social bookmarking domain. And this paper also proposes a friend recommendation system that operates in social bookmarking application domain is based on the behavioral data mining. So this type of mining is able to produce accurate friend recommendation allowing user to get know bookmarks resources that are both novel and serendipitous. With the help of this “interaction overload” & “over specialization” problem is strongly reduced.