Spatial Density-based User Identity Linkage across Social Networks

Abstract

User identity linkage refers to linking different social accounts belonging to the same natural person. Cross social network user identity linkage based on spatiotemporal data has attracted more and more attention. However, the existing methods have some problems such as track processing is not suitable for sparse data and grid processing leads to information loss and abnormality. In view of the above problems, we propose a spatial density-based method VKP, which can accurately and efficiently solve the user identity linkage problem based on spatiotemporal data. According to the sparsity, heterogeneity and imbalance of spatiotemporal data in social networks, the user identity is expressed as several virtual key points, and then the user identity is linked by calculating the similarity between the user identity representations. We compare this method with several state-of-the-art user identity linkage methods based on spatiotemporal data on real datasets, and the results show that this method exceeds the baseline methods in terms of effectiveness and efficiency.