Facebook is tracking coronavirus symptoms by county to identify hotspots

Facebook on Monday released its first map that tracks coronavirus symptoms county by county and plans to update it daily throughout the outbreak.

Facebook partnered with Carnegie Mellon University researchers to create an opt-in survey designed to help identify Covid-19 hotspots before the cases are confirmed. The map breaks down the percentage of people per county who have self-reported coronavirus symptoms, such as loss of smell, cough and fever.

It shows, for example, that 1.45% of people in New York County have reported coronavirus symptoms. But, as you can see in the map below, a huge portion of the map does not have enough participants to show data.

More than 1 million people responded to the survey within the first two weeks, according to Facebook. CEO Mark Zuckerberg said the company will roll out the survey globally this week, which will help it provide a more complete picture.

CNBC Tech: FB Coronavirus symptom map

Facebook’s coronavirus symptom mapFacebook

Facebook has been criticized for its handling of health issues and privacy. Zuckerberg said Monday that Facebook can only see aggregated data. The Carnegie Mellon researchers can see individual survey responses, however.

Zuckerberg stressed that social media platforms have an advantage when it comes to helping health researchers, since they can access large groups of people.

“Facebook is uniquely suited to run these surveys because we serve a global community of billions of people and can do statistically accurate sampling,” Zuckerberg said in a Facebook post. The company said more than 2 billion people use its platform.

In a Washington Post op-ed published Monday, Zuckerberg added that Facebook can help health officials around the world access precise data to make public health decisions in the coming months. 

“This is work that social networks are well-situated to do. By distributing surveys to large numbers of people whose identities we know, we can quickly generate enough signal to correct for biases and ensure sampling is done properly,” he said. 

Read original article here.