基于多元信息融合的用户关联模型

随着社交媒体网站的日益普及,用户倾向于加入多个社交网络,作为社交媒体中的一项新兴工作,将社交网络的多个用户身份关联起来具有重要意义。通过研究目前有代表性的用户关联模型,提出了一个基于综合信息的用户关联模型(BiALP),该模型通过节点表达的方法学习网络的内在结构信息、属性信息和内容信息,以源网络和目标网络的节点表达为特征,以已关联用户对作为带标签数据,采用二分类监督学习的方式学习源网络与目标网络之间的关联关系。大量实验表明,BiALP模型与目前有代表性的其他用户关联模型相比效果有明显的提升(35%),能够实现更精确的用户关联。

Social network user identity linkage model based on comprehensive information

With the increasing popularity of social media sites, users prefer to join multiple online social networks, how to associate multiple user identities in a social network as a new job in social media is of great significance. This paper studies a representative user identity linkage model and proposes a user identity linkage model based on comprehensive information(BiALP). The model learns the internal structure information, attribute information and content information of the network through the node expression method. It is characterized by the node representation of the source network and the target network, and is based on the associated user pairs. With tagged data, the relationship between the source network and the target network is learned through a binary supervised learning manner. A large number of experiments have shown that the BiALP model has a significant improvement(35%)compared to other representative user identity linkage models.