Empirical Dynamic Modelling of the Multi-Source Park Visitation Data

Parks and green-spaces are important for the health and well-being of people in urban areas. Among the many benefits of urban parks are the opportunities to  socialize  and share the experience of nature with others. Recent years have seen an increase in the use of social media for various decision-making purposes in the context of urban computing and smart cities, including the management of public parks. However, as use of readily available social media becomes more mainstream, a critical concern that arises is the extent to which such data remains a valid proxy for people's online and offline behavior over time. Recent works have emerged that report a shift in this proxy relation due to new sets of exogenous biases. In this article, we employ a novel technique based on empirical dynamic modelling to measure this proxy shift and conduct a longitudinal study of the impact of the pandemic on park visitation in four US metropolitan areas. By leveraging data from  SafeGraph and Twitter, we show the validity of Safegraph as a proxy for offline behavior and seek to answer underlying behavioral changes that could have contributed to the proxy shift between the two platforms.