The growth of the Web 2.0 has brought to a widespread use of social media systems. In particular, social bookmarking systems are a form of social media system that allows to tag bookmarks of interest for a user and to share them. The increasing popularity of these systems leads to an increasing number of active users and this implies that each user interacts with too many users (social interaction overload). In order to overcome this problem, we present a friend recommender system in the social bookmarking domain. Recommendations are produced by mining user behavior in a tagging system, analyzing the bookmarks tagged by a user and the frequency of each used tag. Experimental results highlight that, by analyzing both the tagging and bookmarking behavior of a user, our approach is able to mine preferences in a more accurate way, with respect to state-of-the-art approaches that consider only tags.