Group Recommendations: Approaches and Evaluation

Title
Group Recommendations: Approaches and Evaluation
Author
김상욱
Keywords
Recommender system; group recommendation; collaborative filtering
Issue Date
2015-01
Publisher
ACM ICUIMC
Citation
IMCOM '15 Proceedings of the 9th International Conference on Ubiquitous Information Management and Communication , Article No. 105 , Page. 1-6
Abstract
Recommender systems have been an active research topic for the past decade. However, most of previous studies have focused on recommendations to a single user. Recently, as group recommender systems have emerged as an expedient field, several interesting approaches have been proposed. However, despite all of these advances, the current generation of group recommendation approaches still needs further improvements to make more effective recommendations. In this paper, we discuss the limitations of existing group recommendation approaches and present possible developments that could lead to provide better group recommendations. We perform extensive experiments with different group recommendation approaches. The results show that the performance of that group recommendation approaches is limited either by the group type or group size and no single approach consistently performs better than the other approaches. The unavailability of real-life data sets uncovers the doubts for the accuracy of evaluation; the lack of standard terminology/procedure for evaluation also could lead to poor evaluation.
URI
http://hdl.handle.net/20.500.11754/21381http://dl.acm.org/citation.cfm?id=2701208
ISBN
978-1-4503-3377-1
DOI
10.1145/2701126.2701208
Appears in Collections:
COLLEGE OF ENGINEERING[S](공과대학) > COMPUTER SCIENCE AND ENGINEERING(컴퓨터공학부) > Articles
Files in This Item:
There are no files associated with this item.
Export
RIS (EndNote)
XLS (Excel)
XML


qrcode

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

BROWSE