基于Nystrm扩展谱聚类的社会化推荐算法  

Social recommendation algorithm based on spectral clustering with Nystrm extension

作　　者：李振博[1] 徐桂琼[1] 査九 

机构地区：[1]上海大学管理学院,上海200444

出　　处：《计算机应用研究》2015年第11期3238-3241,共4页Application Research of Computers

基　　金：国家自然科学基金资助项目(11201290,61104042)

摘　　要：针对传统协同过滤推荐算法面临的稀疏性、实时性问题,提出了一种适用于朋友关系社交网络的社会化推荐算法。首先使用Nystrm扩展谱聚类方法根据朋友关系对用户进行聚类,然后在用户所属类中寻找最近邻并产生推荐;对用户进行聚类,改善了数据稀疏性问题,用户的聚类过程可离线完成,加快在线推荐速度,提高了系统实时性。在Flixster上的实验结果表明,与传统推荐算法相比,该算法在平均绝对偏差、覆盖率指标上都有较大改善,提高了推荐系统性能。In order to solve the sparsity and real-time problem of traditional recommendation algorithms, this paper proposed a new social recommendation algorithm for the social networks of friends. Firstly, it clustered users with Nystrom extension spectral cluster, mading use of the friend links. Then, it found the nearest neighbors of the user according to the user＇ s clusters and generated recommendations. On the one hand, spectral clustering algorithm could improve the sparsity problem . On the other hand, spectral clustering could performance off-line, which would accelerate the speed of online recommendation and improve the real-time problem. The experimental results on Flixter show that the new algorithm improves recommendation quality in MAE and coverage.

关 键 词：社会化推荐 协同过滤 谱聚类 Nystrom扩展 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程] TP301.6[自动化与计算机技术—控制科学与工程]