Abstract
In context-aware systems, the representation of user profiles can greatly enhance the users' experience. User profiles often requires a compact and, at the same time, expressive language in order to represent conditional preferences, preference relations over the items they contain, and uncertainty labels. This paper presents the use of a possibilistic logic programming framework in a context-aware system to handle user profiles. The framework is able to capture and to process context-dependent preferences and qualitative uncertainty labels which are used to determine which set of preferences should be considered in a given context. Uncertainty labels are used both to select the most plausible preferences for content selection and to keep user profiles up-to-date.