By Topic

A Relational Recommender System Based on Domain Ontology

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
Kapusuzoglu, H. ; Dept. of Comput. Eng., Istanbul Tech. Univ., Istanbul, Turkey ; O╠łguducu, S.G.

Product recommendation on electronic commerce Web sites becomes more important with the widespread use of Internet-based shopping. Collaborative filtering and content based filtering methods have been commonly used for this task by electronic commerce Web sites. These methods have several shortcomings, such as cold start problem, biased ratings problem or inaccurate recommendations. In order to produce effective and accurate recommendations, recent approaches utilize the semantic properties of data by integrating the domain ontology into the recommendation process. In these studies, the domain ontology covering only the types and properties of the product to be recommended is considered where the relational nature of the product data is omitted. However, the domain ontology of the features related to the product may also provide useful information during recommendation process. In this study, we focus on integrating the domain ontology of relational data into the recommendation process. We design a framework for an easy implementation of a recommendation system on relational data. Using this framework, we implement as a case study a recommendation model that recommends books to the users. We evaluated the performance of our model on real data obtained from a Turkish Internet book store. Our experimental results show that our proposed method can be effectively used for recommending items in relational data.

Published in:

Emerging Intelligent Data and Web Technologies (EIDWT), 2011 International Conference on

Date of Conference:

7-9 Sept. 2011