This article explores how contextual information can be used to create intelligent and useful recommender systems. It provides an overview of the multifaceted notion of context, discusses several approaches for incorporating contextual information in the recommendation process, and illustrates the usage of such approaches in several application areas where different types of contexts are exploited. The article concludes by discussing the challenges and future research directions for context-aware recommender systems. 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.
Context-aware recommender systems (CARS) generate more relevant recommendations by adapting them to the specific contextual situation of the user. This article explores how contextual information can be used to create more intelligent and useful recommender systems. It provides an overview of the multifaceted notion of context, discusses several approaches for incorporating contextual information in recommendation process, and illustrates the usage of such approaches in several application areas where different types of contexts are exploited. The article concludes by discussing the challenges and future research directions for context-aware recommender systems.
In this paper, we present some of our work in mobile user modeling following the three steps in a general user modeling process. First, we outline a framework for mobile user activity logging. The framework integrates various hardware and software sensors on smartphones. Second, we have worked on learning relevant user locations for personal information management and recognizing user activities from sensor data to analyze the collected data. Third, the user model can be used to adapt mobile information access, for example in mobile recommender systems. The paper also outlines some requirements for an Activity Context Representation and Exchange Language from the perspective of mobile user modeling.
Homeland security intelligence analysts need help finding relevant information quickly in a rapidly increasing volume of incoming raw data. Many different AI techniques are needed to handle this deluge of data. This paper describes initial investigations in the application of recommender systems to this problem. It illustrates various recommender systems technologies and suggests scenarios for how recommender systems can be applied to support an analyst. Since unclassified data on the search behavior of analysts is hard to obtain we have built a proof-ofconcept demo using analogous search behavior data in the computer science domain. The proof-of-concept collaborative recommender system that we developed is described. Homeland security and other intelligence analysts spend too much time on the mechanics of retrieving relevant information and not enough time on deep analysis. Retrieval usually needs to be initiated by the analyst (i.e., information pull).
The recommendation of additional shopping items that are potentially interesting for the customer has become a standard feature of modern online stores. In academia, research on recommender systems (RS) is mostly centered around approaches that rely on explicit item ratings and long-term user profiles. In practical environments, however, such rating information is often very sparse and for a large fraction of the users very little is known about their preferences. Furthermore, in particular when the shop offers products from a variety of categories, the decision of what should be recommended can strongly depend on the user's current short-term interests and the navigational context. In this paper, we report the results of an initial experimental analysis evaluating the predictive accuracy of different contextualized and non-contextualized recommendation strategies and discuss the question of appropriate experimental designs for such types of evaluations. To that purpose, we introduce a parameterizable protocol that supports session-specific accuracy measurements. Our analysis, which was based on log data obtained from a large online retailer for clothing and lifestyle products, shows that even a comparably simple contextual post-processing approach based on product features can leverage short-term user interests to increase the accuracy of the recommendations.