Posted June 24, 2020
Top photo by Vera Davidova from Unplash
The city of Columbia’s decision Tuesday to require face masks in all businesses to prevent the spread of the coronavirus and the city of Greenville’s decision the day before to require masks in grocery stores and pharmacies are receiving support in South Carolina social media conversations.
The University of South Carolina Social Media Insights Lab analyzed more than 2,500 comments on the issue made since Monday and then used artificial intelligence to better understand emotions associated with the posts. More than 40 percent of the posts generally support the ordinances, about 12 percent are negative and the rest did not express an emotion.
“There has been an ongoing social media debate over the need for masks,” said Kaitlyn Park, lab manager. “The decisions in Columbia and Greenville have brought this debate into focus, with many supporting the measures and others criticizing them. Also, there are calls for cities like Charleston to enact a similar measure.”
The social media accounts with the most influence on these conversations are the city of Columbia, Mayor Steve Benjamin and Governor Henry McMaster. Many of the comments about the governor criticized as insufficient his recommendation that restaurants display decals showing they are following appropriate prevention protocols.
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.
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.