Analyzing Framing through the Casts of Characters in the News

Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 1410–1420, Austin, Texas, November 1-5, 2016. c⃝2016 Association for Computational Linguistics Analyzing Framing through the Casts of Characters in the News Dallas Card1 Justin H. Gross2 Amber E. Boydstun3 Noah A. Smith4 1School of Computer Science, Carnegie Mellon University, Pittsburgh, PA 15213, USA 2Department of Political Science, University of Massachusetts, Amherst, MA 01003, USA 3Department of Political Science, University of California, Davis, CA 95616, USA 4Computer Science & Engineering, University of Washington, WA 98195, USA dcard@cmu.edu aboydstun@ucdavis.edu jhgross@polsci.umass.edu nasmith@cs.washington.edu Abstract We present an unsupervised model for the discovery and clustering of latent “personas” (characterizations of entities). Our model simultaneously clusters documents featuring similar collections of personas. We evalu- ate this model on a collection of news arti- cles about immigration, showing that personas help predict the coarse-grained framing anno- tations in the Media Frames Corpus. We also introduce automated model selection as a fair and robust form of feature evaluation. 1 Introduction Social science tells us that communication almost inescapably involves framing—choosing “a few el- ements of perceived reality and assembling a nar- rative that highlights connections among them to promote a particular interpretation” (Entman, 2007). Memorable examples include loaded phrases (death tax, war on terror), but the literature attests a much wider range of linguistic means toward this end (Pan and Kosicki, 1993; Greene and Resnik, 2009; Choi et al., 2012; Baumer et al., 2015). Framing is associated with several phenomena to which NLP has been applied, including ideology (Lin et al., 2006; Hardisty et al., 2010; Iyyer et al., 2014), sentiment (Pang and Lee, 2008; Feldman, 2013), and stance (Walker et al., 2012; Hasan and Ng, 2013). Although such author attributes are inter- esting, framing scholarship is concerned with persis- tent patterns of representation of particular issues— without necessarily tying these to the states or inten- tions of authors—and the effects that such patterns may have on public opinion and policy. We also note that NLP has often been used in large-scale stud- ies of news and its relation to other social phenom- ena (Leskovec et al., 2009; Gentzkow and Shapiro, 2010; Smith et al., 2013; Niculae et al., 2015). Can framing be automatically recognized? If so, social-scientific studies of framing will be enabled by new measurements, and new applications might bring framing effects to the consciousness of every- day readers. Several recent studies have begun to explore unsupervised framing analysis of political text using autoregressive and hierarchical topic mod- els (Nguyen et al., 2013; Nguyen et al., 2015; Tsur et al., 2015), but most of these conceptualize fram- ing along a single dimension. Rather than trying to place individual articles on a continuum from lib- eral to conservative or positive to negative, we are interested in discovering broad-based patterns in the ways in which the media communicate about issues. Here, our focus is on the narratives found in news stories, specifically the participants in those stories. Insofar as journalists make use of archetypal narra- …

Content truncated to 500 words