基于快速社区检测的协同过滤推荐算法  

Collaborative filter recommendation algorithm based on fast community detection

作　　者：蒋盛益[1] 杨博泓 吴美玲[2] 

机构地区：[1]广东外语外贸大学信息学院,广东广州510006 [2]广东外语外贸大学国际工商管理学院,广东广州510006

出　　处：《广西大学学报（自然科学版）》2013年第6期1408-1412,共5页Journal of Guangxi University（Natural Science Edition）

基　　金：国家自然科学基金资助项目(61070061);广东省普通高校科技创新资助项目(2012KJCX0049);国家科技支撑计划资助项目(2012BAH02F03);广东省产学研结合资助项目(2012B091100353)

摘　　要：随着社交网络服务的快速发展,推荐服务亦以各种形式融入到社交网络服务之中。由于社交网络服务数据量大,如何快速高效地处理数据成为迫在眉睫的问题。基于这一研究背景,提出一种能够快速得到较好推荐结果的基于快速社区检测的协同过滤推荐算法。实验结果表明,与传统的协同过滤推荐算法相比,提出的算法可以得到更好的推荐结果和更少的时间开销。With the rapid development of social network services, recommending service has also been integrated into the social network services in various forms. However, as the social network services tend to contain larger data, how to process data quickly and efficiently has become an ur- gent problem. To solve this problem, a fast community-detection-based collaborative filtering recom- mendation algorithm, which can achieve better recommended results quickly, is presented in this paper. Experimental results show that this algorithm can improve performance of the traditional col- laborative filter in both recommendation efficiency and quality.

关 键 词：社区检测 协同过滤 推荐算法 社交网络 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]