Our research consortium develops user modeling methods for proactive applications. In this project we use machine learning methods for predicting users’ preferences from implicit relevance feedback. Our prototype application is information retrieval, where the feedback signal is measured from eye movements or user’s behavior. Relevance of a read text is extracted from the feedback signal with models learned from a collected data set. Since it is hard to define relevance in general, we have constructed an experimental setting where relevance is known a priori.