Posted October 5, 2019
By Rebekah Friedman, communications manager, rebekahb@mailbox.sc.edu, 803-576-7270
Photo courtesy of Gage Skidmore
Sen. Kamala Harris received more positive social media mentions in South Carolina in October than Joe Biden and Elizabeth Warren, the two leaders for the Democratic presidential nomination in RealClear Politics’ composite average of the leading national political polls.
According to a new analysis by the University of South Carolina’s Social Media Insights Lab, Harris’ positive sentiment has been increasing steadily since July. She also was the top influencer last month on social media conversations about the Democratic presidential hopefuls and she was the most tagged Democratic presidential candidates on Twitter in the state. Both of these trends follow discussions about her decision to pull out of the Columbia forum where President Trump received a criminal justice reform award.
“The female candidates remain the candidates to watch on social media. While September was a great month for Elizabeth Warren on social in South Carolina, in October we see that Kamala Harris has outperformed Warren in both share of voice and positive sentiment,” said Kaitlyn Park, Insights Lab manager. “For now, Harris is almost tied with Bernie Sanders in these categories.”
Joe Biden continues to be the Democratic candidate who receives the most mentions, though he ranks last in positive mentions among the top candidates. Bernie Sanders ranks second for the month in both share of voice and positive mentions. Despite buzz about Sanders’ heart attack in early October, he saw an increase in positive sentiment and share of voice.
Pete Buttigieg had the smallest share of voice, but those talking about him like him. Buttigieg has led in positive sentiment since the Insights Lab started tracking the candidates last March.
“Joe Biden is being pulled down in South Carolina because of his association with Ukraine,” said Park. “While Biden is still the top dog in name recognition, he continues to drop in positive sentiment.”
Since March, the lab has analyzed more than 380,000 posts about the leading Democratic candidates – nearly 78,000 of which were in October alone.
About the Insights Index
The lab assesses conversation volume and sentiment percentages for the leading Democratic
candidates at the close of each month as part of its new Insights Index project. The
lab also examines conversations for trends and patterns related to the candidates’
activities.
How does the lab choose which candidates to track?
Leading candidates are identified using polling data from RealClearPolitics.
How is sentiment calculated?
The lab uses software developed by Crimson Hexagon, now known as BrandWatch following
a recent 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.
About the Social Media Insights Lab
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 graph files, contact Rebekah Friedman at rebekahb@mailbox.sc.edu or 803-576-7270.