The aether soon will be pervaded with a high density of digital services for usage on mobile phones. Personalization plays a crucial role for the success and acceptance of such systems. In this paper, we present work in progress on a new approach for improving the personalization of recommender systems for pervasive services. Mobile utilization is extended from services inherent in devices to pervasive services. We describe a new concept for collaborative and content-based filtering based on the users’ service rankings given by arrangement of menu icons and discuss different models for interaction with a varying icon menu. Categories and Subject Descriptors H.3.3 [Information Search and Retrieval]: Information filtering, relevance feedback General Terms Design, Human Factors. Keywords Personalization, context-awareness, touch-based interaction.