Interest based selection of user generated content for rich multimedia services

In view of the overwhelming popularity of user generated content, both in terms of production and consumption, new intelligent services are needed to help users finding the content they need and enhance existing services with suitably selected content. In this paper we present a set of algorithms for retrieving content, based on dynamic user profiles and learning capabilities (e.g. based on user feedback). The profile information is used in content searches as well as for assisting the user input analysis process (i.e. speech recognition). To illustrate the approach taken, a rich communication service is presented. Here, the basic service (i.e. voice/video conferencing) is enhanced by showing pictures in real time to the users based on the topic of their conversation and their specific interests.