Interactive linguistics tool detects political 'framing'

Media Contact

Joe Schwartz

As communication strategists gear up for the 2016 presidential campaign – trying to manipulate public opinion with “message framing” – communication researchers are recruiting political news junkies in a nationwide test of a tool called FrameCheck.

Volunteers sought
Volunteer field test subjects can apply to join the FrameCheck study by completing a brief online survey and installing the plug-in.

FrameCheck is an interactive tool, in the form of a web browser plug-in, to draw attention to framing in political issues, according to Eric P.S. Baumer, research associate in communication and information science at Cornell.

“If you open an article online at The New York Times or The Wall Street Journal or the BBC, you’re not going to know in advance which words and phrases are most related to framing,” Baumer says. “So the question is: Can we identify those features automatically and draw people’s attention to framing – as a means of mitigating the influence of framing effects?”

Volunteers in the two-month field study may choose any news site on which to run the FrameCheck plug-in. As volunteer readers peruse each article, FrameCheck runs in the background, analyzing text and identifying words and phrases most related to framing.

“For instance, an article about health care – framed to emphasize issues of cost – might use language that talks about Medicaid, insurance premiums, costs for patients or tax burdens,” Baumer explains. “In contrast, an article that frames health care in terms of equality might describe economic or racial disparities, gaps between the majority and minorities or differences in the quality of care that different patients receive.”

Frame-checking technology is described in two upcoming publications by Baumer and collaborators at Cornell and the University of California, Irvine: “Testing and Comparing Computational Approaches for Identifying the Language of Framing in Political News” (Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics – Human Language Technologies) and “A Simple Intervention to Reduce Framing Effects in Perceptions of Global Climate Change” (in-press at the journal Environmental Communication).

The research is funded, in part, with a grant from the National Science Foundation’s Social-Computational Systems Program. 


Story Contacts