Social Media COVID-19 Contact Tracing Using Mobile Social Payments and Facebook Data (2303.02374v1)

Abstract: Many in the US were reluctant to report their COVID-19 cases at the height of the pandemic (e.g., for fear of missing work or other obligations due to quarantine mandates). Other methods such as using public social media data can therefore help augment current approaches to surveilling pandemics. This study evaluated the effectiveness of using social media data as a data source for tracking public health pandemics. There have been several attempts at using social media data from platforms like Twitter for analyzing the COVID-19 pandemic. While these provide a multitude of useful insights, new platforms like Venmo, a popular U.S. mobile social payment app often used during in-person activities, remain understudied. We developed unique computational methods (combining Venmo- and Facebook- derived data) to classify post content, including the location where the content was likely posted. This approach enabled geotemporal COVID-19-related infoveillance. By examining 135M publicly available Venmo transactions from 22.1M unique users, we found significant spikes in the use of COVID-19 related keywords in March 2020. Using Facebook-based geotags for 9K users along with transaction geo-parsing (i.e., parsing text to detect place names), we identified 38K location-based clusters. Within these groups, we found a strong correlation (0.81) between the use of COVID-19 keywords in a region and the number of reported COVID-19 cases as well as an aggregate decrease in transactions during lockdowns and an increase when lockdowns are lifted. Surprisingly, we saw a weak negative correlation between the number of transactions and reported cases over time (-0.49). Our results indicate that using non-Twitter social media trace data can aid pandemic- and other health-related infoveillance.