Back

Case Study: Using Facebook Data to Monitor Adherence to Stay-at-home Orders in Colorado and Utah

Layer, R. M.; Fosdick, B.; Larremore, D. B.; Bradshaw, M.; Doherty, P.

2020-07-30 public and global health
10.1101/2020.06.04.20122093 medRxiv
Show abstract

In the absence of effective treatments, social distancing has been the only public health measure available to combat the COVID-19 pandemic. In the US, implementing this response has been left to state, county, and city officials, and many localities have issued some form of a stay-at-home order. Without existing tools and with limited resources, localities struggled to understand how their orders changed behavior. In response, several technology companies opened access to their users location data. As part of the COVID-19 Data Mobility Network, we obtained access to Facebook User data and developed four key metrics and visualizations to monitor various aspects of adherence to stay at home orders. These metrics were carefully incorporated into static and interactive visualizations for dissemination to local officials. All code is open source and freely available at https://github.com/ryanlayer/COvid19

Matching journals

The top 8 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.