Recommender Systems, based on Collaborative filtering techniques, recommend contents based on the opinions of other users, which makes it imperative to aggregate similar users as accurately as possible. Most of the Collaborative Filtering based Recommender Systems use profile vector directly for similarity evaluation. A few recent researches have explored the possibility of using Ontology for evaluating similarity but all the aspects of Ontology have not yet been exploited. In this paper we propose an ‘Enhanced Ontology based Profile Comparison’ mechanism for better similarity evaluation. This mechanism expands the profile vector components in one user profile on the basis of explicit semantic relations. The expanded results are then compared with the other user’s expanded profile vector components using a predefined Relationship Weightage Scheme. This facilitates better recommender aggregation and hence improves the quality of recommendations. The proposed mechanism can be used for Content Based Filtering as well.
CITATION STYLE
Bora, R. P., Bhandari, C., & Mehta, A. (2009). Enhanced Ontology Based Profile Comparison Mechanism for Better Recommendation (pp. 345–352). https://doi.org/10.1007/978-3-642-00563-3_36
Mendeley helps you to discover research relevant for your work.