smsociety14 has ended
Sunday, September 28 • 11:01 - 11:20
"Topic Modeling with Sentiment Evaluation for Analysis of Opinion Polarization"

Sign up or log in to save this to your schedule and see who's attending!

Background: It is widely recognized that U.S. national politics have become more polarized over the last several decades, and that the proliferation of partisan news outlets (talk radio stations, partisan news channels, news web sites, and blogs) has contributed to public opinion polarization. While qualitative research has identified a number of rhetorical strategies used by partisan news outlets, including overgeneralization, sensationalism, misleading and inaccurate information, ad hominem attacks, and belittling ridicule of opponents, that produce polarizing emotional reactions in audiences (Sobieraj and Berry 2011), research on how consumption of partisan news may influence audience attitudes has been held back by measurement problems (Prior 2013).

Objective: We present a new text analysis technique, topic modeling with sentiment evaluation (TMSE), that combines four methodological elements (precise multiple-sample selection, topic models with latent semantic analysis, sentiment analysis, and correspondence analysis) in order to compare the degree of polarization of topics across text collections produced by social groups.

Methods: We demonstrate TMSE by analyzing reactions to the Trayvon Martin controversy in spring 2012 by commenters on two partisan news websites (the Daily Caller and the Huffington Post, with approx. 4000 lines and 130,000 words per sample).

Results: Based on studies of news media as an outrage industry (Berry and Sobieraj 2014) and of political pundit inaccuracy (Tetlock 2006), we predict that high-profile commentators will be more polarizing than other news personalities and topics. Results of the TMSE analysis support this prediction.

Berry, J. M., and S. Sobieraj. (2014). The outrage industry: Political opinion media and the new incivility. Oxford, UK: Oxford University Press.

Prior, M. (2013). Media and political polarization. Annual Review of Political Science, 16, 101-127.

Sobieraj, S., J. M. Berry. (2011). From incivility to outrage: Political discourse in blogs, talk radio, and cable news. Political Communication, 28(1): 19-41.

Tetlock, Philip E. (2006). Expert political judgment: How good is it? How can we know? Princeton, NJ: Princeton University Press.


Nick Evangelopoulos

University of North Texas

Gabe Ignatow

Associate Professor, University of North Texas
text mining, text analysis methods, sociology, theory, Bourdieu, new media And I love to talk about my startup company GradTrek.com, a graduate school recommendation engine (similar to Match.com and Pandora).

Konstantinos Zougris

University of North Texas

Sunday September 28, 2014 11:01 - 11:20
TRS 1-149 Ted Rogers School of Management

Attendees (0)