AI reveals major differences in how social media users debate vaccinations and climate change

WATERLOO, Ontario — Both climate change and vaccinations tend to be divisive subjects nowadays. Interestingly, however, scientists are using artificial intelligence to show how the debate on social media over these two topics are vastly different. In a nutshell, social media users are more open to discussion and differing views regarding climate change, whereas online vaccination conversations tend to be more biased or one-sided.

Study authors from the University of Waterloo created and trained a machine-learning algorithm to analyze roughly 87 million tweets posted online discussing either vaccines or climate change between 2007 and 2016. The AI system revealed online sentiments regarding climate change are “overwhelmingly” on the “pro side,” meaning most users believe global warming is real, brought on mainly due to human actions, and requires immediate attention. Notably, most social media users discussing climate change were also open to interacting with other users holding opposite climate change beliefs.

Vaccinations are a make-or-break issue for many

Observations regarding online discussions about vaccines were much more varied. To start, only about 15 to 20 percent of users displayed clear cut pro-vaccine beliefs. Seventy percent expressed no strong sentiment on vaccines either way. Importantly, both individuals and entire online communities holding one vaccine belief were largely unwilling to engage with anyone of a different opinion.

YouTube video

“It is an open question whether these differences in user sentiment and social media echo chambers concerning vaccines created the conditions for highly polarized vaccine sentiment when the COVID-19 vaccines began to roll out,” says Chris Bauch, a professor of applied mathematics, in a university release. “If we were to do the same study today with data from the past two years, the results might be wildly different. Vaccination is a much hotter topic right now and appears to be much more polarized given the ongoing pandemic.”

Vaccines controversial even before COVID

The research team originally set out to determine if any sentiments on climate change and vaccination were related. For example, how do people who care about these topics create online communities in the first place? Also, just how much do online behaviors influence real-life decisions, beliefs, and outcomes?

“There’s been some work done on the polarization of opinions in Twitter and other social media,” explains Madhur Anand, professor of environmental sciences at the University of Guelph. “Most other research looks at these as isolated issues, but we wanted to look at these two issues of climate change and vaccination side-by-side. Both issues have social and environmental components, and there are lots to learn in this research pairing.”

The tweets analyzed for this project, of course, pre-date the COVID-19 pandemic by a few years. Still, study authors conclude these findings provide a compelling look at online vaccine sentiments in the immediate years leading up to the coronavirus pandemic.

“We expected to find that user sentiment and how users formed networks and communities to be more or less the same for both issues,” Prof. Bauch concludes. “But actually, we found that the way climate change discourse and vaccine discourse worked on Twitter were quite different.”

The findings appear in the journal Humanities and Social Sciences Communications.

Follow on Google News

About the Author

John Anderer

Born blue in the face, John has been writing professionally for over a decade and covering the latest scientific research for StudyFinds since 2019. His work has been featured by Business Insider, Eat This Not That!, MSN, Ladders, and Yahoo!

Studies and abstracts can be confusing and awkwardly worded. He prides himself on making such content easy to read, understand, and apply to one’s everyday life.

The contents of this website do not constitute advice and are provided for informational purposes only. See our full disclaimer