A recent study conducted by the University of Rochester sheds light on the increasing ideological polarization evident in news stories about domestic politics and social issues.

The researchers employed machine learning techniques to analyze a vast collection of 1.8 million news headlines from major US news outlets, spanning the years 2014 to 2022.

While it is widely acknowledged that news media outlets often adopt ideological perspectives in their articles, previous studies on the matter have been limited in scope and relied on small sample sizes.

Ideological leanings

By leveraging machine learning, the researchers were able to conduct a comprehensive analysis of headlines across nine representative media outlets, including the New York Times, Bloomberg, CNN, NBC, the Wall Street Journal, Christian Science Monitor, the Federalist, Reason, and the Washington Times.

To measure the nuanced thematic discrepancies among headlines, the study employed a technique called multiple correspondence analysis. The researchers categorized the news stories into four distinct categories—domestic politics, economic issues, social issues, and foreign affairs—and examined how media outlets with left, right, and central leanings differed in their choice of language within these categories.

Interestingly, the researchers found that US media outlets spanning the political spectrum exhibited consistency and similarity in their coverage of economic issues. Discrepancies emerged primarily in the reporting of foreign affairs, which the researchers attributed to variations in individual journalistic styles.

For instance, the Wall Street Journal and Bloomberg were noted for their emphasis on the economic and financial implications of geopolitical tensions, which led to differing perspectives compared to other media outlets. However, when it came to domestic politics and social issues, significant differences were evident among the headlines of various media outlets.

Subtle differences

“We observed a lot of subtle differences in the words they choose when they cover the same high-level topics,” the researchers say. “For example, when covering abortion issues, Reason tends to use the term ‘abortion law,’ while CNN underscores its ideological position by using the term ‘abortion rights.’ On a higher level they are both talking about abortion issues, but you can feel the subtle difference in the words that they choose.”

They hope to dive deeper into the topic and try and understand how the media use different words to try and cover the same topics. They believe that if these discrepancies can be understood, and how this feeds into media bias, it can be crucial for both the media industry and readers alike.

“For consumers, it’s useful to know this information because the echo chamber effect is very strong and people are used to only listening to things they like to hear,” the researchers conclude. “Showing the divergence and the increased partisanship may make them aware that they need to be more conscious consumers of news.”