Please use this identifier to cite or link to this item:
Title: The importance of similarity metrics for representative users identification in recommender systems
Authors: Georgiou, Olga 
Tsapatsoulis, Nicolas 
Keywords: Artificial intelligence;Recommender systems;Information technology
Category: Media and Communications
Field: Social Sciences
Issue Date: 2010
Publisher: Springer
Source: Artificial intelligence applications and innovations: 6th IFIP WG 12.5 international conference, AIAI 2010, Larnaca, Cyprus, October 6-7, 2010. Proceedings. Pages 12-21
Abstract: In this paper we explore the efficiency of recommendation provided by representative users on behalf of cluster members. Clustering is used to moderate the scalability and diversity issues faced by most recommendation algorithms face. We show through extended evaluation experiments that cluster representative make successful recommendations outperforming the K-nearest neighbor approach which is common in recommender systems that are based on collaborative filtering. However, selection of representative users depends heavily on the similarity metric that is used to identify users with similar preferences. It is shown that the use of different similarity metrics leads, in general, to different representative users while the commonly used Pearson coefficient is the poorest similarity metric in terms of representative user identification
ISBN: 978-3-642-16238-1 (print)
ISSN: 978-3-642-16239-8 (online)
DOI: 10.1007/978-3-642-16239-8_5
Rights: © 2010 IFIP
Type: Book Chapter
Appears in Collections:Κεφάλαια βιβλίων/Book chapters

Files in This Item:
File Description SizeFormat
Tsapatsoulis_The importance of similarity metrics for.pdf130.58 kBAdobe PDFView/Open
Show full item record

Citations 50

checked on Dec 17, 2018

Page view(s)

Last Week
Last month
checked on Aug 19, 2019


checked on Aug 19, 2019

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.