Learning user preferences in a system combining pervasive behaviour and social networking

Pervasive computing is an important paradigm for interacting with the increasingly complex environment surrounding the user while social networking is equally important for handling the daily interactions between users. One challenge that has been identified recently is to bring these two paradigms together in an integrated way so that the user has the advantages of both, together with benefits arising from the combination of the two. This is the aim of the SOCIETIES project which is developing a system that combines general pervasive system behaviour with social networking in a seamless fashion. One of the important features on which the system is based, is that of context aware personalization, and major components in the SOCIETIES system include those of personalization and context management. Within this, one of the major challenges is that of building up a set of user preferences to obtain the best predictions, especially since users will change their minds about preferences from time to time. To achieve this two different approaches (rule-based and neural net) are used by the system to represent user preferences. This paper describes the smart space approach developed in the Persist project and currently being expanded in SOCIETIES, and then focuses on the problem of managing user preferences. The rule-based approach is described in detail and the neural net approach only briefly. The strategy used employs both approaches and compares the predictions of the two to obtain the best accuracy and adaptability.