Overview of Data

Highland Math publishes a free COVID-19 dataset on Snowflake Marketplace, AWS Data Exchange and Data.World. The consolidated public data sets pertain to the pandemic and its societal impact.

The data has three different tables of data. First is the table that contains daily counts by state of the number of reported positive, negative, and pending tests, and the number of hospitalizations and deaths. The second table contains a comparison of current daily TSA checkpoint counts with corresponding counts from the prior year. The third table contains daily counts of popular Covid19 hashtags and accompanying hashtags seen in tweets with popular Covid19 hashtags.

There’s been an incredible amount of data being collected and shared for the purposes of understanding the current situation around the world. A few weeks ago we wrote about three different ways location data was being collected to analyze the Coronavirus – read that here. Other marketplaces, like data.world, have even created resource hubs to help consolidate the data. 


Example Use Cases

Case Counts

  • Compare different states’ case counts, rate of increase in positive tests, and more. 
  • Join data to an external table that tracks daily weather in order to compute correlations between new positive tests on a given date and the temperature in the days preceding that date. 
  • Match daily case counts to internal metrics to see the effect of daily state cases on business.

Twitter and TSA Travel Figures

  • Analyze how Coronavirus has ultimately affected social media discourse, and how the prevalence of certain hashtags compares to case count prevalence over time.
  • Compute correlation of travel counts with tweets containing popular coronavirus hashtags.