^{Posted Aug. 12, 2020
Top photo from Kamala Harris' Twitter}

---

Joe Biden’s selection of Kamala Harris as his vice-presidential running mate has South Carolinians talking. The Social Media Insights Lab at the University of South Carolina reviewed more than 17,000 posts about Harris made since the announcement late Tuesday afternoon.  The lab found that among comments containing sentiment, 54.3 percent were positive and 45.7 percent were critical of the selection. 

 

“The divisions in our country are reflected in this outpouring of opinion, which is unusually heavy,” said Kaitlyn Park, Insights Lab manager.  “Among her supporters, Harris was praised as intelligent, successful and a fighter. To her detractors, Harris is seen as selling out to Biden, whom she criticized during the Democratic primaries, and as someone who made questionable decisions as a prosecutor .”

The lab used artificial intelligence to better understand these conversations.  The emotion expressed most frequently was joy, seen in 20 percent of the posts, followed by sadness (12 percent) and disgust (eight percent). 

 

“There clearly was a lot of excitement among Democrats, but many South Carolinians remain skeptical about the selection,” said Park.  Some commenters said they are looking forward to the debate between Harris and Vice President Pence. 

---

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.