移动社交网络中基于网络中心度的链路预测方法*

移动社交网络中的链路预测是指通过已知的网络节点以及移动社交网络结构等信息预测网络中尚未产生连边的两个节点之间产生链接的可能性。基于网络中心度的思想,提出一种适用于移动社交网络的链路预测算法。在该算法中,根据节点网络中心度和共同邻居数来计算两个节点的相似性指标,两个节点的共同邻居数越多、共同邻居的网络中心度越高,则两个节点的相似度越高。另外,由于移动社交网络的动态性特征,还将考虑时间因素对预测结果的影响。将该方法与其他4种常用的链路预测方法进行比较,实验结果显示所提方法要优于其他方法。

A link prediction algorithm based on network centrality in mobile social networks

Link prediction aims at estimating the likelihood of the existence of links between nodes in mobile social networks. A method based on centrality of common neighbors was proposed for link prediction in mobile social networks. In this method, the node similarity is calculated based on both the node centrality and the number of common neighbors. If the two nodes have more common neighbors and the node centrality of the common neighbors is higher, the similarity of two nodes are higher. In addition, the temporal information is considered due to the fact that the behavior of links as time goes by. The experimental results show that the performance of the improved algorithm is superior to the four traditional link prediction algorithms.