Issue No. 03 - May/June (2007 vol. 22)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/MIS.2007.58
Gediminas Adomavicius , University of Minnesota
YoungOk Kwon , University of Minnesota
Traditional single-rating recommender systems have been successful in a number of personalization applications, but the research area of multicriteria recommender systems has been largely untouched. Taking full advantage of multicriteria ratings in various applications requires new recommendation techniques. The authors propose two new approaches—a similarity-based approach and an aggregation-function-based approach—to incorporating and leveraging multicriteria rating information in recommender systems. They discuss multiple variations of each proposed approach and report empirical analysis results from a real-world dataset. Experimental results show that recommender systems can leverage multicriteria ratings and improve recommendation accuracy, as compared to traditional single-rating recommendation techniques.
personalization, recommender systems, collaborative filtering, multicriteria ratings, rating estimation
Y. Kwon and G. Adomavicius, "New Recommendation Techniques for Multicriteria Rating Systems," in IEEE Intelligent Systems, vol. 22, no. , pp. 48-55, 2007.