移动社交网络中隐社交行为的研究  

A Study on Implicit Social Behavior in Mobile Social Networks

作　　者：刘蔚[1] 胡昌龙[1] 

机构地区：[1]湖北工业大学经济与管理学院,湖北武汉430068

出　　处：《湖北工业大学学报》2016年第3期56-59,67,共5页Journal of Hubei University of Technology

基　　金：国家社会科学基金项目(14BTQ045);教育部人文社会科学研究项目资助(13YJC870015)

摘　　要：移动社交网络本质上是一个用户之间拥有信任关系的动态虚拟网路,可以通过群体间存在于现实世界的一些属性,推断出用户之间的信任关系水平,使整个在线群体的信任关系得以支撑。提出一种集群的算法框架,可以通过分布式的分区来产生一个集群的细粒度层次结构,并从中提取实际的群体特征,以解决集群重叠的问题。基于上述算法所构造的一个隐社交行为图形,包含了足够多用来评估集群内部个体之间信任关系的信息。使用隐社交行为图形理论,可以进一步计算出分组信任值;通过讨论组内信任值的聚合和传递,可以计算出全局移动社交网络中的集群信任和间接的信任值。Mobile social networks are essentially a dynamic virtual network with a trust relationship among the users, from which the level of this trust among users can be inferred on the basis of some properties in the real world so as to support the trust relationship between the online groups. A Framework of a clustering algorithm is proposed in this article so that a cluster of fine granularity hierarchy can be produced by using distributed partitioned and the actual groups in response to overlapping clusters can be extracted. Based on the algorithm above, an implicit social graph can be constructed, which contains enough information to assess the relationship of trust among individuals within the cluster. Through the use of the implicit social graph theory the grouped trust value can be further calculated. Through the aggregate and transfer of trust within the group, group trust and indirect trust value can be computed in the global mobile social networks.

关 键 词：移动社交网络 集群行为感知 隐社交行为 

分 类 号：G350.7[文化科学—情报学]