Authors:
Ugur Ceylan
1
and
Aysenur Birturk
2
Affiliations:
1
Baskent University, Turkey
;
2
METU, Turkey
Keyword(s):
Content-boosted collaborative filtering, Semantic similarity, Ontology, Sparsity, Item cold-start.
Related
Ontology
Subjects/Areas/Topics:
Data Engineering
;
Ontologies and the Semantic Web
;
Ontology and the Semantic Web
;
Web Information Systems and Technologies
;
Web Interfaces and Applications
;
Web Personalization
Abstract:
Collaborative filtering is one of the most used recommendation approaches in recommender systems. However, collaborative filtering systems have some major problems such as sparsity, scalability and cold-start problems. In this paper we focus on the sparsity and item cold-start problems in collaborative filtering in order to improve the quality of recommendations. We propose an approach that uses semantic similarities between items based on a priori defined ontology-based metadata in the movie domain. According to the semantic similarities between items and past user preferences, recommendations are made. The results of the evaluation phase show that our approach improves the quality of recommendations.