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.
Social Connectedness Index
On the Interplay of Regional Mobility, Social Connectedness, and the Spread of COVID-19 in Germany
In this paper we investigate the impact of human mobility and social connectivity derived from Facebook activities on the weekly rate of new infections in Germany between March 3rd and June 22nd, 2020. Our results confirm that reduced social activity lowers the infection rate, accounting for regional and temporal patterns. The extent of social distancing, quantified by the percentage of people staying put within a federal administrative district, has an overall negative effect on the incidence of infections.
Movement Range Maps
Combining Graph Neural Networks and Spatio-temporal Disease Models to Predict COVID-19 Cases in Germany
We propose a trade-off between both research directions and present a multimodal learning approach that combines the advantages of statistical regression and machine learning models for predicting local COVID19 cases in Germany. This novel approach enables the use of a richer collection of data types, including mobility flows and colocation probabilities, and yields the lowest MSE scores throughout our observational period in our benchmark study.
Disease Prevention Maps
Transfer Graph Neural Networks for Pandemic Forecasting
We utilize graph representation learning to capitalize on the underlying relationship of population movement with the spread of COVID-19. Specifically, we create a graph where nodes correspond to a country's regions and the edge weights denote human mobility from one region to another. Then, we employ graph neural networks to predict the number of future cases. Experimental results on 4 European countries demonstrate the superiority of our method.
Population Density Maps
Population Counts: Aiming Humanitarian Mappers at populated areas with Disaster Ninja
When a disaster strikes, better maps enable better response. Humanitarian OpenStreetMap Team (HOT) often coordinates emergency mappers at the request of organizations like the Red Cross, or as an OpenStreetMap initiative. Such preparatory work may take a while, from several hours to an entire working day. During fast-unfolding emergencies, a few hours here and there make a big difference. That’s where Kontur was able to streamline the process through technology. Kontur created a Disaster Ninja dashboard.
Social Connectedness Index
No inventor is an island: social connectedness and the geography of knowledge flows in the US
Do informal social ties connecting inventors across distant places promote knowledge flows between them? To measure informal ties, we use a new and direct index of social connectedness of regions based on aggregate Facebook friendships. We identify a significant and robust effect of informal ties on patent citation.
Quantifying the dynamics of migration after Hurricane Maria in Puerto Rico
Understanding the population composition and distribution of a region affected by a major natural disaster is vital for the allocation of resources to communities in need and critical to inform mortality estimates. The utilization of social media traces, coupled with mobile phone data, could provide live estimates of post-disaster population changes in disaster-affected areas.