Ideological Perspective Detection Using Semantic Features

Proceedings of the Fourth Joint Conference on Lexical and Computational Semantics (*SEM 2015), pages 137–146, Denver, Colorado, June 4–5, 2015. Ideological Perspective Detection Using Semantic Features Heba Elfardy Columbia University New York, NY heba@cs.columbia.edu Mona Diab George Washington University Washington, DC mtdiab@gwu.edu Chris Callison-Burch University of Pennsylvania Philadelphia, PA ccb@cis.upenn.edu Abstract In this paper, we propose the use of word sense disambiguation and latent semantic features to automatically identify a person’s perspective from his/her written text. We run an Ama- zon Mechanical Turk experiment where we ask Turkers to answer a set of constrained and open-ended political questions drawn from the American National Election Studies (ANES). We then extract the proposed features from the answers to the open-ended questions and use them to predict the answer to one of the constrained questions, namely, their pre- ferred Presidential Candidate. In addition to this newly created dataset, we also evaluate our proposed approach on a second standard dataset of “Ideological-Debates”. This lat- ter dataset contains topics from four domains: Abortion, Creationism, Gun Rights and Gay- Rights. Experimental results show that us- ing word sense disambiguation and latent- semantics, whether separately or combined, beats the majority and random baselines on the cross-validation and held-out-test sets for both the ANES and the four domains of the “Ideo- logical Debates” datasets. Moreover combin- ing both feature sets outperforms a stronger unigram-only classification system. 1 Introduction With the pervasiveness of social media and online discussion fora, there has been a significant increase in documented political and ideological discussions. Automatically predicting the perspective or stance of users in such media is a challenging research problem that has a wide variety of applications in- cluding recommendation systems, targeted advertis- ing, political polling, product reviews and even pre- dicting possible future events. Ideology refers to the beliefs that influence an individual’s goals, ex- pectations and views of the world (Van Dijk, 1998; Ahmed and Xing, 2010). The ideological perspec- tive of a person is often expressed in his/her choice of discussed topics. People with opposing per- spectives will choose to make different topics more salient. (Entman, 1993). From a social-science viewpoint, the notion of “perspective” is related to the concept of “framing”. Framing involves making some topics (or some as- pects of the discussed topics) more prominent in or- der to promote the views and interpretations of the writer (communicator). The communicator makes these framing decisions either consciously or uncon- sciously (Entman, 1993). These decisions are often expressed in the lexical choice. For example, a per- son who holds anti-abortion views, is more likely to use the terms “life” and “kill” whereas a person who is pro a woman having an option to go for an abor- tion will often stress on “choice”. From a computational viewpoint, work on perspective-detection is closely related to subjectiv- ity and sentiment analysis. One’s perspective nor- mally influences his/her sentiment towards different topics or targets. Conversely identifying the senti- ment of a person towards multiple targets can serve as a cue for identifying …

Content truncated to 500 words