Over the past two years, dozens of organizations used Facebook's Data for Good products to improve wellbeing and save lives. Their most profound applications include disaster preparedness projects, vaccination campaigns, and effective deployment of services during times of natural disaster.
Data on Economic Anxiety Offer New Opportunities for Insights on the Global Effects of the COVID-19 Pandemic
We recently released a new set of aggregated data on economic indicators, which will provide new insights into how individuals have been affected by the COVID-19 pandemic worldwide. Economic concerns due to COVID-19 are widespread, but it has been challenging to examine those concerns in a systematic way due to a lack of multinational data. Using our new data from the COVID-19 Symptom Survey, which addresses many of these concerns, we explored a few questions related to the prevalence and trends of economic anxiety.
Home for the Holidays? The Impact of US Holidays on Social Behaviors and Preventative Measures
With pandemic fatigue setting in across the United States after a long year filled with uncertainty, many felt the temptation to celebrate a “normal” Thanksgiving and Christmas. Many health organizations strongly discouraged large gatherings during the holidays. Delphi’s COVID-19 Surveys can provide a broader picture of the travel Americans took during the holiday season. In taking greater risks with travel, did Americans change their behaviors in other preventative measures like mask wearing during this time?
Tracking Global COVID-19 Vaccination Uptake and Sentiments in 200+ Countries and Territories
In December, the University of Maryland and Carnegie Mellon University, in partnership with Facebook, began collaborating with the U.S. Centers for Disease Control and Prevention (CDC) to incorporate a COVID-19 vaccination module in the Symptom Survey to support the COVID-19 vaccination programs that are rolling out globally. The newly added questions will enable our survey to track daily vaccination uptake, measure vaccine-related sentiments, and examine how trends vary across different population subgroups in real-time.
Social Connectedness Index
Predicting County-Level COVID-19 Cases using Spatiotemporal Machine Learning: Modeling Human Interactions using Social Media and Cell-Phone Data
In this study, we first compare the power of Facebook’s social connectedness with cell phone-derived human mobility for predicting county level new cases of COVID-19. Our experiments show that social connectedness is a better proxy for measuring human interactions leading to new infections. Comparing our predictions with a baseline currently used by the CDC indicates an average 58% improvement in prediction over two-to-four week prediction horizons, pointing to the strong predictive power of our model.
Movement Range Maps
Supporting the Government Response to COVID-19 Using Facebook Mobility Data: Chile
Researchers collaborated with Chilean ministries to integrate socio-economic data with Facebook mobility data, exploring why some districts were not adhering as strongly to social distancing policies, quarantines, and other measures. Integrating the social economic data showed that some socio-economic groups were traveling a longer distance than others. This helped them further understand that people in lower socio-economic status were likely traveling for money and also traveling frequently to access food.
Movement Range Maps
Movement of people in Jakarta during COVID-19 crisis: an analysis using Facebook’s Disease Prevention Maps data
Similar with the above research, CSIS is trying to capture the movement of people in Jakarta as the Jakarta Provincial Government implemented social restrictions in the province. The research found that people in Jakarta still have high mobility regardless of the restrictions, indicating high cases of non-compliance among the people. There are movements of people up to 40-60 kms and even up to 500 kms, from Jakarta to surrounding cities.