Posted July 9, 2020
As coronavirus cases increase in South Carolina, so too are social media conversations nationwide about the Palmetto State and its growing problem with COVID-19.
The University of South Carolina Social Media Insights Lab has identified more than 21,000 comments made since July 1 about South Carolina and the coronavirus. Many of them shared a report in The New York Times that looked at how states in the U.S. compare to other countries in terms of the most confirmed cases over the last week, adjusted for population size. South Carolina ranked third behind Arizona and Florida but ahead of every other country in the world.
“The New York Times story provided context for the situation in South Carolina,” said Kaitlyn Park, Insights Lab manager. “We know that the number of coronavirus cases here is going up, but many did not realize we are a worldwide hotspot for COVID-19.”
MSNBC anchor Rachel Maddow was a top influencer in these conversations. Maddow compared South Carolina to Estonia, Iceland, Norway and Ireland, which each had fewer than 200 infections over the past two weeks. South Carolina had more than 20,000.
Another influencer was S.C. State Rep. Mandy Powers Norrell, who tweeted: “In person classroom instruction is very important. However…. On the day we learn that SC has the 3rd fastest growing rate of COVID cases per capita *in the world,* it’s time to focus on the most basic needs of safety.”
As Park explained, “The social media conversations we reviewed are not painting a positive picture of South Carolina.”
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. How is sentiment calculated?
About the Social Media Insights Lab
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.
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.
How is sentiment calculated?