Posted October 8, 2020
In a U.S. Senate race the Cook Political Report says is a toss up, Democratic candidate Jaime Harrison is seeing a significant uptick in support on social media, according to a new analysis by the University of South Carolina Social Media Insights Lab.
The lab analyzed more than 12,000 South Carolina posts made since Oct. 1 mentioning Harrison or his opponent, U.S. Sen. Lindsey Graham. Comments about Harrison spiked after Saturday’s televised between the two. Harrison has a larger share of voice with higher positives and fewer negatives.
“People like Jaime Harrison and he has received a lot of positive comments on social media,” said Kaitlyn Park, Insights Lab manager. “Graham, though, was better known and had the larger share of voice. That changed with the debate and that is potentially significant.”
The highest volume for both came during the debate when Graham called the Democratic Party “nuts” and Harrison responded by comparing Graham’s attitude to Harrison’s six-year-old child.
The lab used artificial intelligence to measure positive and negative sentiment for the candidates. Among the posts mentioning Harrison, 24 percent were positive. By comparison, 20 percent of the posts mentioning Graham were positive.
As for negative comments, 24 percent of the posts mentioning Harrison were negative vs. 32 percent for posts mentioning Graham. About half of all comments were neutral and did not express sentiment.
On Twitter, top hashtags included #sendlindseyhome, #lindseymustgo and #2facedlindsey.
“Comments on social reflect only a portion of South Carolina voters, but if they are any indication, Lindsey Graham is facing a serious challenge,” said Park.
The Insights Lab has been tracking the Graham-Harrison race since July. You can find earlier reports here.
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, Brandwatch Consumer Research, formerly known as 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 email@example.com or 803-576-7270.
How is sentiment calculated?
The lab uses software, Brandwatch Consumer Research, formerly known as Crimson Hexagon. 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.