No abstract

The paper presents a multidimensional (MD) approach to recommender systems that can provide recommendations based on additional contextual information besides the typical information on users and items used in most of the current recommender systems. This approach supports multiple dimensions, extensive profiling, and hierarchical aggregation of recommendations. The paper also presents a multidimensional rating estimation method capable of selecting two-dimensional segments of ratings pertinent to the recommendation context and applying standard collaborative filtering or other traditional two-dimensional rating estimation techniques to these segments. A comparison of the multidimensional and two-dimensional rating estimation approaches is made, and the tradeoffs between the two are studied. Moreover, the paper introduces a combined rating estimation method that identifies the situations where the MD approach outperforms the standard two-dimensional approach and uses the MD approach in those situations and the standard two-dimensional approach elsewhere. Finally, the paper presents a pilot empirical study of the combined approach, using a multidimensional movie recommender system that was developed for implementing this approach and testing its performance.2

raditional recommender systems, such as those based on content-based and collaborative filtering, tend to use fairly simple user models. For example, user-based collaborative filtering generally models the user as a vector of item ratings. As additional observations are made about users' preferences, the user models are extended, and the full collection of user preferences is used to generate recommendations or make predictions. This approach, therefore, ignores the notion of "situated actions" (Suchman 1987), the fact that users interact with the system within a particular "context" and that preferences for items within one context may be different from those in another context.In many application domains, a context-independent representation may lose predictive power because potentially useful information from multiple contexts is aggregated. For example, when a user is buying books, the preferences the user expresses in one context, such as "books for my children," may be of no predictive value when the user seeks recommendations in a different context, such as "work-related books." The ideal contextaware recommendation system would, therefore, be able reliably to label each user action with an appropriate context and effectively tailor the system output to the user in that given context.The concept of "context" has been studied extensively in several areas of computing and other disciplines. For example, Bazire and Brezillon (2005) examine and compare some 150 different definitions of context from a number of different fields and conclude that the multifaceted nature of the concept makes it difficult to find a unifying definition: "Is context a frame for a given object? Is it the set of elements that have any influence on the object? Is it possible to define context a priori or just state Articles

No abstract