People Recommendation in Social Platforms based on User Interaction Profiles
25 July 2011
In this paper we present a methodology to learn user profiles from content shared by people in Social Platforms. Such profiles are specifically tailored to reflect the user's degree of interactivity related to each topic of interest, i.e. their potential motivation to engage in conversations related to their topic. Ranking users based on their level of interactivity on a given topic can facilitate people the seamless access to trusted information from friends or other users who can help them in their information needs, translated either explicitly by a question or implicitly by the task they perform on a Computer.
