Cell phone mobility data and manifold learning: Insights into population behavior during the COVID-19 pandemic

Abstract

AbstractAs COVID-19 cases resurge in the United States, understanding the complex interplay between human behavior, disease transmission, and non-pharmaceutical interventions during the pandemic could provide valuable insights to focus future public health efforts. Cell-phone mobility data offers a modern measurement instrument to investigate human mobility and behavior at an unprecedented scale. We investigate mobility data collected, aggregated, and anonymized by SafeGraph Inc. which measures how populations at the census-block-group geographic scale stayed at home in California, Georgia, Texas, and Washington since the beginning of the pandemic. Using manifold learning techniques, we find patterns of mobility behavior that align with stay-at-home orders, correlate with socioeconomic factors, cluster geographically, and reveal sub-populations that likely migrated out of urban areas. The analysis and approach provides policy makers a framework for interpreting mobility data and behavior to inform actions aimed at curbing the spread of COVID-19.