Sensing the pulse of urban activity centers leveraging bike sharing open data

Understanding social activities in Urban Activity Centers can benefit both urban authorities and citizens. Traditionally, monitoring large social activities usually incurs significant costs of human labor and time. Fortunately, with the recent booming of urban open data, a wide variety of human digital footprints have become openly accessible, providing us with new opportunities to understand the social dynamics in the cities. In this paper, we resort to urban open data from bike sharing systems, and propose a two-phase framework to identify social activities in Urban Activity Centers based on bike sharing open data. More specifically, we first detect bike usage anomalies from the bike trip data, and then identify the potential social activities from the detected anomalies using a proposed heuristic method by considering both spatial and temporal constraints. We evaluate our framework based on the large-scale real-world dataset collected from the bike sharing system of Washington, D.C. The results show that our framework can efficiently identify social activities in different types of Urban Activity Centers and outperforms the baseline approach. In particular, our framework can identify 89% of the social activities in the major Urban Activity Centers of Washington, D.C.