Issue No. 03 - May/June (2007 vol. 22)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/MIS.2007.55
Silvana Aciar , University of Girona, Spain
Debbie Zhang , University of Technology, Sydney
Simeon Simoff , University of Technology, Sydney
John Debenham , University of Technology, Sydney
Consumer reviews, opinions, and shared experiences in using a product are a powerful source of information that recommender systems can use. Despite the importance and value of such information, no comprehensive mechanism formalizes the opinions' selection, retrieval, and use owing to the difficulty of extracting information from text data. A new recommender system prioritizes consumer product reviews on the basis of the reviewer's level of expertise in using a product. The system uses text mining techniques to map each piece of each review comment into an ontology. Using consumer reviews also helps solve the cold-start problem that plagues traditional approaches. This article is part of a special issue on Recommender Systems.
ontology, reviews acquisition, recommender systems, text mining
D. Zhang, S. Simoff, J. Debenham and S. Aciar, "Informed Recommender: Basing Recommendations on Consumer Product Reviews," in IEEE Intelligent Systems, vol. 22, no. , pp. 39-47, 2007.