中国科学院重庆绿色智能技术研究院机构知识库

QQ客服 官方微博 反馈留言

	Coarse cluster enhancing collaborative recommendation for social network systems
	Zhao, Yao-Dong1,2; Cai, Shi-Min1,2; Tang, Ming1,2; Shang, Min-Sheng2,3
	2017-10-01
摘要	Traditional collaborative filtering based recommender systems for social network systems bring very high demands on time complexity due to computing similarities of all pairs of users via resource usages and annotation actions, which thus strongly suppresses recommending speed. In this paper, to overcome this drawback, we propose a novel approach, namely coarse cluster that partitions similar users and associated items at a high speed to enhance user-based collaborative filtering, and then develop a fast collaborative user model for the social tagging systems. The experimental results based on Delicious dataset show that the proposed model is able to dramatically reduce the processing time cost greater than 90% and relatively improve the accuracy in comparison with the ordinary user-based collaborative filtering, and is robust for the initial parameter. Most importantly, the proposed model can be conveniently extended by introducing more users' information (e.g., profiles) and practically applied for the large-scale social network systems to enhance the recommending speed without accuracy loss. (C) 2017 Elsevier B.V. All rights reserved.
关键词	Recommender system Social network system Social tagging system Tripartite graph Time complexity Collaborative user model
DOI	10.1016/j.physa.2017.04.131
URL	查看原文
发表期刊	PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS
ISSN	0378-4371
卷号	483页码:209-218
收录类别	SCI
WOS记录号	WOS:000405062000021
语种	英语