BLACKSBURG, Va. — The political divide seemingly gets worse every day and a recent study points the finger at cable news networks. Virginia Tech researchers say that national news giants CNN and Fox News don’t just mirror the rising political polarization in America — their increasingly partisan broadcasts are deepening the divide, especially in the digital realm of social media.
Eugenia Rho, an assistant professor in computer science at Virginia Tech, employed artificial intelligence (AI) to understand how repeated media broadcasts influence public discourse on significant societal matters.
“When we’re talking about language that is mediatized and played over and over and over by actors who are influential, how does that affect the way the public talks about important social issues?” questions Rho in a university release. “Rigorous analysis of big data sets like this opens whole new avenues of understanding media and its impact.”
Mike Horning, a former journalist and current associate professor in communication, emphasized the evolution of media bias research.
“Historically, if we were to tackle a question that was about media bias in the past 40 years, it’s going to be somebody looking at a data set of maybe 500 articles. That is very limited,” notes Horning. “But computer scientists are now able to help us tackle some of these tough, tough questions by analyzing massive amounts of data, which we’ve never been able to do before. So that’s why I think it’s super cool to be able to work with them.”
To comprehend the extent of this partisan broadcast, the team utilized a form of AI known as natural language processing. Their analysis covered almost 300 billion words from CNN and Fox News broadcasts and examined roughly 133,000 tweets linked to these networks from 2010 to 2020. They aimed to identify if these national broadcasts contained biased and inflammatory content and whether such content influenced the networks’ followers on social media platforms like X, previously known as Twitter.
The data sources included:
- Transcriptions of 24/7 broadcasts by CNN and Fox News from 2010 to 2020, provided by the Internet Archive and Stanford Cable TV News Analyzer.
- Tweets from 2010-2020 related to six contentious political subjects, authored by users who engaged with or followed both @CNN and @FoxNews.
The research underscored that Americans predominantly consume news from TV, often selecting their sources based on pre-existing political biases. Rho and Horning’s findings highlight that broadcast language significantly determines how viewers engage in national debates on social platforms. For instance, Fox News immigration discussions frequently featured words like “illegal” and “order,” while CNN highlighted terms like “parents” and “communities.” In a matter of months, these linguistic patterns manifested in X discussions among the respective network’s followers.
“This country was founded upon the Declaration of Independence. Words have immense, immense power, and a tangible impact on people’s lives,” says Rho. “When we have this consistent pattern in which major broadcast networks diverge completely, to the extent that they’re portraying an almost different reality in which topics are discussed, then you have this irreconcilable division across audiences. That’s something that I hope this paper is able to foster more discussion around.”
Addressing the polarization seems challenging due to economic pressures.
“Part of the motivation for it has been the increasing decline of viewership in cable news. They are competing against everything on the web,” says Horning. “How can you cut through all the noise? The solution often is to become more outlandish and more rowdy. Because TV news is driven by ratings, the incentive is to make market-driven decisions that probably are not democratic.”
Horning added that “partisan broadcast news is contributing to levels of polarization amongst the electorate.”
“And we have terabytes of data to prove that,” says Horning. “It’s not just some college professors who studied something for two weeks. We now have 10 years of data. But getting the news to cover itself is going to be the hard part.”
“As a computer scientist, being able to show this pattern at scale, I hope that it generates the necessary conversations around what’s good for the collective society. Because if people just can’t be on the same page to talk about important issues, where do we go from here?” Rho concludes.
The study was presented at the Proceedings of the Seventeenth International AAAI Conference on Web and Social Media.
You might also be interested in:
- Obsessively watching the news can make you mentally and physically sick
- The kindness cure: Good news counteracts bad effects from negative media reports
- Fake or just biased? Study finds news credibility depends on more than just facts