How urban places are visited by social groups? Evidence from matrix factorization on mobile phone data

This research attempts to build a unified framework for distinguishing the spatiotemporal visit patterns of urban places by different social groups using mobile phone data in Harbin, China. Social groups are detected by their social ties in the ego-to-ego mobile phone call network and are embedded in physical space according to their home locations. Popular urban places are detected from user-generated content as the basic spatial analysis unit. Coupling subscribers' footprints and urban places in physical space, the spatiotemporal visit patterns of urban places by distinct social groups are uncovered and interpreted by non-negative matrix factorization. The proposed framework enables us to answer several critical questions from three perspectives: (1) How to model popular urban places in terms of vague boundary, land use, and semantic features based on crowdsourcing data?; (2) How to evaluate interaction between individuals for inspecting the relationship between spatial proximity and social ties based on spatiotemporal co-occurrence?; and (3) How to distinguish urban place visit preferences for social groups associated with different socio-demographic characteristics? Our research could assist urban planners and municipal managers to identify critical urban places frequented by different population groups according to their roles and social/cultural characteristics for improvement of urban facility allocation.