Proceedings of the ACL 2014 Workshop on Language Technologies and Computational Social Science

Abstract

in Baltimore, following the 52nd annual meeting of the ACL. The workshop's goal was to increase the visibility of computational social science-in which automated techniques are applied to massive datasets to answer scientific questions about society-for ACL researchers and to help build connections between language technologists and social scientists.The workshop included six invited talks from researchers who have successfully brought language technologies to computational social science research questions: political scientists Amber Boydstun and Justin Grimmer, social computing expert Ed Chi, sociolinguist Sali Tagliamonte, and computational linguists Lillian Lee and Philip Resnik.Out of twenty submissions of short papers, thirteen were selected by the program committee for poster presentation. These represent an exciting, conversation-provoking range of research projects.The workshop also included a session reporting on a related research competition, the NLP Unshared Task in PoliInformatics. A short overview paper is included in these proceedings.This workshop was supported by grants from Google and the U.S. National Science Foudnation (grant IIS-1433108). These funds enabled the participation of the invited speakers, fourteen graduate students, and three more senior researchers.We thank the invited speakers, program committee members, authors, and participants for sharing time and thoughts on this increasingly important research topic.Cristian Danescu-Niculescu-Mizil, Jacob Eisenstein, Kathy McKeown, and Noah Smith AbstractLouis Armstrong (is said to have) said, "I don't need words -it's all in the phrasing". As someone who does natural-language processing for a living, I'm a big fan of words; but lately, my collaborators and I have been studying aspects of phrasing (in the linguistic, rather than musical sense) that go beyond just the selection of one particular word over another. I'll describe some of these projects in this talk. The issues we'll consider include: Does the way in which something is worded in and of itself have an effect on whether it is remembered or attracts attention, beyond its content or context? Can we characterize how different sides in a debate frame their arguments, in a way that goes beyond specific lexical choice (e.g., "pro-choice" vs. "pro-life")? The settings we'll explore range from movie quotes that achieve cultural prominence; to posts on Facebook, Wikipedia, Twitter, and the arXiv; to framing in public discourse on the inclusion of geneticallymodified organisms in food. AbstractParty brands are central to theories of Congressional action. While previous work assumes that a party's brand-its long run reputation-is a direct consequence of the content of legislation, in this presentation I show how partisans from both parties use public statements to craft their own party's reputation and to undermine their opponents party. The incentive to craft and destroy brands varies across legislators, creating systematic distortions in who contributes to partisan branding efforts, ...