Semantic-Enhanced Personalized Recommender System

• Published in: 2007 International Conference on Machine Learning and Cybernetics Vol. 7; pp. 4069 - 4074
• Main Authors: Rui-Qin Wang, Fan-Sheng Kong
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.08.2007
• Subjects: Clustering; Clustering algorithms; Collaboration; Collaborative filter; Cybernetics; Information filtering; Information filters; Machine learning; Ontologies; Ontology; Personalized recommendation; Recommender systems; Scalability; Semantic information; Software libraries
• ISBN: 1424409721; 9781424409723
• ISSN: 2160-133X
• DOI: 10.1109/ICMLC.2007.4370858

Personalized recommender systems have emerged as a powerful method for improving both the content of customers and the profit of providers in e-business environment. Nowadays, many kinds of recommender methods have been proposed to provide personalized services. However, all these techniques have not made full use of the semantic information of objects, which leading them to an unsatisfying performance. Collaborative filter (CF) system, as the most popular personalized recommender systems, has such well-known limitations as sparsity, scalability and cold-start problem. A semantic-enhanced collaborative recommender system is proposed in this paper. The semantic information of objects is extracted to support the recommendation process. This study compares the performance of the proposed technique with the traditional CF approaches. Experimental results demonstrate the effectiveness of the proposed method.