USC study: Political discourse on Twitter helped predict COVID outbreak sites

Political discourse on Twitter helps to predict where future COVID-19 outbreaks are likely to occur, offering a tool that could help health officials to proactively respond, according to a study released Thursday by USC researchers.

“We show that anti-science views are aligned with political ideology, specifically conservatism,” said Kristina Lerman, the study’s lead author and a professor at the USC Viterbi School of Engineering. “While that’s not necessarily brand new, we discovered this entirely from social media data that gives detailed clues about where COVID-19 is likely to spread so we can take preventive measures.”

Researchers said they found that “anti-science” attitudes posted between January and April 2020 were high in some Mountain West and Southern states that were later hit with deadly COVID-19 surges. The study’s findings can help policymakers and public health officials by allowing them to tailor messages to mitigate distrust of science and prepare for a potential disease outbreak if they see anti-science sentiment growing in one region of the country, according to Lerman.

The study, published in the Journal of Medical Internet Research, examined public health attitudes based on 27 million tweets by 2.4 million Twitter users in the United States between Jan. 21 and May 1, 2020, parsed the data by demographics and geography in an approach that allowed for near real-time monitoring of partisan and “pseudo-science” attitudes that could be refined in high detail aided by advanced computing techniques, according to Lerman.

Researchers were able to track attitudes across time and geography to see how they changed and found that polarization on the topic of science went down over time, suggesting that most people are ready to accept scientific evidence and trust scientists, she said.

The ability to track public discourse around coronavirus and compare it with epidemiological outcomes emerged as a result of the study, according to Lerman, a computer scientist and expert in mining social media for clues about human behavior at USC’s Information Sciences Institute.

“Now we can use social media data for science, to create spatial and temporal maps of public opinions along ideological lines, pro- and anti-science lines,” Lerman said. “We can also see what topics are important to these segments of society, and we can plan proactively to prevent disease outbreaks from happening.”