Skip to Content

Coronavirus: Get complete details about the university's response to COVID-19.

College of Information and Communications

  • Women wearing a mask looking at a computer screen

Coronavirus concerns increasing in South Carolina

Posted June 22, 2020
Top photo by Engin Akyurt from Unplash


As the number of coronavirus cases reported this month in South Carolina has steadily increased, so too have social media conversations about COVID-19.

An analysis by the University of South Carolina Social Media Insights Lab of more than 73,000 social media posts in the state since June 1 shows that in the middle of the month concerns started to increase. There have been more than 12,000 posts in the past three days.

“People clearly wanted to put the coronavirus behind them,” said Kaitlyn Park, manager of the Insights Lab. “But as case numbers have gone up, a lot of people are concerned and are warning others to take COVID-19 precautions more seriously.”

The lab used artificial intelligence to better understand emotions associated with these conversations. The dominant feeling was sadness, with comments about grief, funerals and loss. There was some joy, though, with users expressing positive feelings over the work of medical workers and others.


About the Social Media Insights Lab

The lab is part of the College of Information and Communications. It is used for teaching, academic research and public reports intended to help people better understand issues of the day.

The Insights Lab software, Crimson Hexagon, uses artificial intelligence to interpret data. View a full list of reports and follow the lab on Twitter at @UofSCInsights.

For media inquiries or to request graphic files, contact Rebekah Friedman at rebekahb@mailbox.sc.edu or 803-576-7270.

How is sentiment calculated?
The lab uses software developed by Crimson Hexagon, now known as BrandWatch following a merger. The software gauges the emotional tone of conversations using auto-sentiment artificial intelligence technology. This feature is useful for identifying patterns within large sets of social media data, but it should be noted that auto-sentiment has its limits. For example, it does not always recognize sarcasm, nor does it account for posts which may express more than one emotion.


Challenge the conventional. Create the exceptional. No Limits.

©