2nd Workshop on Context-Aware Recommender Systems (CARS-2010) Barcelona, Spain - September 26, 2010 Joint event with Challenge on Context-Aware Movie Recommenders In conjunction with the 4th ACM Conference on Recommender Systems

Bamshad Mobasher. "Contextual User Modeling for Recommendation."

Abstract. The role of recommender systems as a fundamental utility for electronic commerce and information access is well established with many commercially-available recommender systems providing benefits to both users and businesses. But, recommender systems tend to use very simplistic user models that are additive in nature: new user preferences are simply added to the existing profiles. This additive approach ignores the notion of "situated action," that is, the fact that users interact with systems within a particular context and items relevant within one context may be irrelevant in another.

Little agreement exists among researchers as to what constitutes context, but its importance seems undisputed. In psychology, a change in context during learning has been shown to have an impact on recall suggesting a key role played by context in the structure and processing of human memory. Research in linguistics has shown that context plays the important role of a disambiguation function. More recently, the role of context has been explored in intelligent information systems, including in Web search and collaborative recommender systems. In particular, a variety of approaches and architectures have emerged for incorporating context or situational awareness in the recommendation process. This research shows that context can play an important role in improving the performance and usefulness of recommender systems.

In this talk, I will provide a broad overview of the problem of contextual recommendation and some of the recent solutions proposed by researchers and practitioners. I will also specifically focus on two perspectives (from among many) on integrating context in user modeling for personalized recommendation: one that is inspired by a model of human memory and emphasizes the modeling of context based on observations of user behavior; and another that emphasizes the role of domain knowledge and semantics as an integral part of user context. The goal of this talk is to provide a starting point for further discussion of contextual recommendation.

Biographical Sketch. Bamshad Mobasher is a Professor of Computer Science and the director of the Center for Web Intelligence at the School of Computing of DePaul University in Chicago. His research areas include Web mining, Web personalization, recommender systems, predictive user modeling, and information retrieval. Prior to DePaul he was an assistant professor of Computer Science at the University of Minnesota, Twin Cities, where he did some seminal work in Web mining. He has published more than 120 scientific articles, numerous book chapters, and several edited books in these areas. He has served as an organizer and on the program committees of numerous conferences, including as a program chair and steering committee member of the ACM International Conference on Recommender Systems. As the director of the Center for Web Intelligence, Dr. Mobasher is directing research in Web mining, Web analytics, and personalization, as well as overseeing several related joint projects with the industry. His recent activities include co-editing a volume, "Intelligent Techniques for Web Personalization", published by Springer, culminating from a series of successful international workshops on the same topic; and co-editing special issues of ACM Transactions on Internet Technologies and User Modeling and User-Adapted Interaction on data mining for personalization. He has also been one of the founding organizers of the highly successful WebKDD workshops on Knowledge discovery on the Web which have been held at ACM SIGKDD conference for the past 10 years. Dr. Mobasher serves as an associate editor for the ACM Transactions on the Web and on the editorial boards of several other prominent computing journals, including User Modeling and User-Adapted Interaction, and the Journal of Web Semantics.

This workshop builds upon the success of the 1st Workshop on Context-Aware Recommender Systems (CARS-2009) held in New York in October 2009, which brought together an international group of researchers to explore the importance and use of contextual information in recommender systems as well as to discuss new research directions.

The importance of contextual information has been recognized by researchers and practitioners in many disciplines, including e-commerce personalization, information retrieval, ubiquitous and mobile computing, data mining, marketing, and management. While a substantial amount of research has already been performed in the area of recommender systems, the vast majority of existing approaches focuses on recommending the most relevant items to users and does not take into account any additional contextual information, such as time, location, weather, or the company of other people. Therefore, this workshop aims to bring together researchers with wide-ranging backgrounds to identify important research questions, to exchange ideas from different research disciplines, and, more generally, to facilitate discussion and innovation in the area of context-aware recommender systems (CARS).

In particular, topics of interest for this workshop include (but are not limited to):

• Context modeling techniques for recommender systems;
• Context-aware user modeling for recommender systems;
• Data sets for context-dependent recommendations;
• Algorithms for detecting the relevance of contextual data;
• Algorithms for incorporating contextual information into recommendation process;
• Algorithms for building explicit dependencies between contextual features and ratings;
• Interacting with context-aware recommender systems;
• Novel applications for context-aware recommender systems;
• Large-scale context-aware recommender systems;
• Evaluation of context-aware recommender systems.

In case the main topic of the paper is a challenging dataset for context-aware recommender systems, the author(s) should describe the data model and the main features of this dataset, and make the dataset available for the research community.

Paper submission. The length of submissions is 5 pages in the standard ACM SIG proceedings format. Microsoft Word and LaTeX templates for papers in ACM SIG format are provided here. All submissions must be in English and the files should be in PDF format. Paper submissions and reviews will be handled electronically; each paper will be evaluated by the workshop program committee based on originality, significance, technical soundness, and clarity. All papers must be submitted through the CARS-2010 page on the EasyChair conference management site .

Accepted papers. The accepted papers will be made available on the workshop website, and their authors will present their work in front of the workshop audience. The workshop will not request the copyright transfer from the authors; therefore, after receiving feedback at the workshop, the authors will be able to submit the improved versions of their papers to conferences and journals (the workshop organizers are currently exploring the possibilities to organize a special issue on this topic in some research journal).

Last modified: September 16, 2010