基于随机游走算法的社会化标签的用户推荐

被引:3
作者
王海雷 [1 ,2 ]
俞学宁 [3 ]
机构
[1] 北京大学光华管理学院
[2] 中国民生银行博士后工作站
[3] 中国民生银行科研培训学院
关键词
社会化标签; 用户; 资源; 标签; 推荐;
D O I
10.16208/j.issn1000-7024.2013.07.026
中图分类号
TP391.3 [检索机];
学科分类号
081203 ; 0835 ;
摘要
利用来自Delicious的数据集,结合内容相似度的挖掘和语义关系处理,对社会化标签系统的用户推荐的算法进行了研究。具体工作为:利用标签和书签的语义关系,定义用户的内容信息,从而计算内容相似度;建立内容相似度与社会网络的用户链接关系,通过可重启的随机游走算法(RWR)结合来达成理想的效果。实验评测显示,无论是精确度还是召回率,该算法的效果都要明显优于baseline的算法。
引用
收藏
页码:2388 / 2391
页数:4
相关论文
共 11 条
[1]  
Ran-dom-walk computation of similarities between nodes of agraph,with application to collaborative recommendation. Fouss Francois,Pirotte Alain,Jean-Michel R,et al. IEEE Transactions on Knowledge and Data Engineering . 2007
[2]  
Structure learning ofBayesian networks using constraints. Cassio P de Campos,Zeng Zhi,Ji Qiang. Proceedings of the 26th Annual InternationalConference on Machine Learning . 2009
[3]  
Personalized reco-mmender system based on item taxonomy and folksonomy. Liang Huizhi,Xu Yue,Li Yuefeng,et al. Proceedings of the 19th ACM Inter-national Conference on Information and Knowledge Manage-ment . 2010
[4]  
Multiverse recommen-dation:n-dimensional tensor factorization for context-aware collaborative filter-ing. KARATZOGLOU A,AMATRIAIN X,BALTRUNAS L, et al. Proceedings of the fourth ACM conference on Recommender systems . 2010
[5]  
A recommender system based on tag and time information for social tagging systems. Nan Zheng,Qiudan Li. Expert Systems With Applications . 2011
[6]  
Stable adaptive neuralnetwork control. Ge S S,Hang C C,Lee T H,et al. . 2010
[7]  
Incorporating heterogeneous infor-mation for personalized tag recommendation in social taggingsystems. Feng Wei,Wang Jianyong. Proceedings of the 18th ACMSIGKDD International Conference on Knowledge Discovery andData Mining . 2012
[8]   基于信任模型的协同过滤推荐算法 [J].
夏小伍 ;
王卫平 .
计算机工程, 2011, 37 (21) :26-28
[9]  
Genetic algorithm for text cluste-ring based on latent semantic indexing. Song Wei,Park Soon Cheol. Computers&Mathematics with Applications . 2009
[10]  
Collaboration and semantics in flickr:From social interaction to se-mantic similarity. Capocci Andrea,Baldassarri Andrea,Servedio Vito D P,et al. Proceedingsof the International Workshop on Modeling Social Media . 2010