Human mobility, social ties, and link prediction

TLDR

Our understanding of how individual mobility patterns shape and impact the social network is limited but essential for a deeper grasp of network dynamics and evolution, and this question remains largely unexplored due to the difficulty of obtaining large‑scale society‑wide data that capture both movements and social interactions. The study aims to address this challenge by tracking trajectories and communication records of 6 million mobile phone users and to investigate how mobility correlations can predict new links in a social network. The authors track trajectories and communication records of 6 million users and analyze how mobility correlations can be used to predict new links in the network. They find that movement similarity strongly correlates with social proximity, that mobility measures alone predict new links as well as traditional network measures, and that a supervised classifier combining mobility and network features further improves prediction accuracy, offering new insights into link prediction and network dynamics.

Abstract

Our understanding of how individual mobility patterns shape and impact the social network is limited, but is essential for a deeper understanding of network dynamics and evolution. This question is largely unexplored, partly due to the difficulty in obtaining large-scale society-wide data that simultaneously capture the dynamical information on individual movements and social interactions. Here we address this challenge for the first time by tracking the trajectories and communication records of 6 Million mobile phone users. We find that the similarity between two individuals' movements strongly correlates with their proximity in the social network. We further investigate how the predictive power hidden in such correlations can be exploited to address a challenging problem: which new links will develop in a social network. We show that mobility measures alone yield surprising predictive power, comparable to traditional network-based measures. Furthermore, the prediction accuracy can be significantly improved by learning a supervised classifier based on combined mobility and network measures. We believe our findings on the interplay of mobility patterns and social ties offer new perspectives on not only link prediction but also network dynamics.