Quest: An Adaptive Framework for User Profile Acquisition from Social Communities of Interest

Within this paper we introduce a framework for semi- to full-automatic discovery and acquisition of bag-of-words style interest profiles from openly accessible Social Web communities. To do such, we construct a semantic taxonomy search tree from target domain (domain towards which we´re acquiring profiles for), starting with generic concepts at root down to specific-level instances at leaves, then we utilize one of proposed Quest methods, namely Depth-based, N-Split and Greedy to read the concept labels from the tree and crawl the source Social Network for profiles containing corresponding topics. Cached profiles are then mined in a two-step approach, using a clusterer and a classifier to generate predictive model presenting weighted profiles, which are used later on by a semantic recommender to suggest and recommend the community members with the items of their similar interest.