Serendipitous Bookmark Recommendations in a Social Bookmarking System using Behavioral Data Mining

Social media systems allow users to share resources with the people connected to them. In order to handle the exponential growth of the content in these systems and of the amount of users that populate them, recommender systems have been introduced. A form of social media, known as Social Bookmarking System, allows users to share bookmarks in a social network. It also allows users to use tags to describe resources that are of interest for them, helping to organize and share these resources with other users in the network. By analyzing users with a similar behavior (i.e., users who have a large amount of tags and resources in common,) accurate recommendations can be produced. This paper proposes a bookmark recommender system that operates in the social bookmarking application domain and is based on behavioral data mining. Experimental results show how this type of mining is able to produce serendipitous bookmark recommendations. Using this approach, the impact of the “interaction overload� and the “over-specialization� problems is strongly reduced.