Workshop on Machine Learning for User Modeling : Challenges Edinburgh , Scotland 24

Adaptive information systems typically exploit knowledge about the user’s interests, preferences, goals etc. to determine wha t should be presented to the user and how this presentation should take place. When de aling with mobile users, however, information about their motions—the place s visited, the duration of stays, average velocity etc.—can be additionally exploi ted to enrich the user model and better adapt the system behavior to the user’s need s. This paper discusses what type of positioning data and background knowled ge is required to achieve such a motion-based adaptation of information prov ision and how it can be implemented using a variety of mostly standard machine-l earning techniques.