Context relevance assessment for recommender systems

Research on context aware recommender systems is taking for granted that context matters. But, often attempts to show the influence of context have failed. In this paper we consider the problem of quantitatively assessing context relevance. For this purpose we are assuming that users can imagine a situation described by a contextual feature, and judge if this feature is relevant for their decision making task. We have designed a UI suited for acquiring such information in a travel planning scenario. In fact, this interface is generic and can also be used for other domains (e.g., music). The experimental results show that it is possible to identify the contextual factors that are relevant for the given task and that the relevancy depends on the type of the place of interest to be included in the plan.