Friends with Motives: Using Text to Infer Influence on SCOTUS

Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 1724–1733, Austin, Texas, November 1-5, 2016. c⃝2016 Association for Computational Linguistics Friends with Motives: Using Text to Infer Influence on SCOTUS Yanchuan Sim Language Technologies Institute Carnegie Mellon University Pittsburgh, PA 15213, USA ysim@cs.cmu.edu Bryan R. Routledge Tepper School of Business Carnegie Mellon University Pittsburgh, PA 15213, USA routledge@cmu.edu Noah A. Smith Computer Science & Engineering University of Washington Seattle, WA 98195, USA nasmith@cs.washington.edu Abstract We present a probabilistic model of the in- fluence of language on the behavior of the U.S. Supreme Court, specifically influence of amicus briefs on Court decisions and opin- ions. The approach assumes that amici are rational, utility-maximizing agents who try to win votes or affect the language of court opin- ions. Our model leads to improved predictions of justices’ votes and perplexity of opinion language. It is amenable to inspection, allow- ing us to explore inferences about the persua- siveness of different amici and influenceability of different justices; these are consistent with earlier findings. “Language is the central tool of our trade.” John G. Roberts, 2007 (Garner, 2010) 1 Introduction The Supreme Court of the United States (SCOTUS), the highest court in the American judiciary, makes decisions with far-reaching effects. In a typical case, there are four participating parties: petitioners and respondents who file briefs arguing the merits of their sides of a case (“merits briefs”); third-party en- tities with an interest (but not a direct stake) in the case, who file amicus curiae1 briefs to provide fur- ther arguments and recommendations on either side; and justices who, after oral arguments and discus- 1Amicus curiae is Latin for “friends of the court.” Hereafter, we use amicus in singular and amici in plural to refer to these interested third parties. It is common for several amici to co- author a single brief, which we account for in our model. sions, vote on the case and write “opinions” to ex- plain the Court’s decisions.2 In recent years, amicus briefs are increasingly be- ing employed as a lobbying tool to influence the Court’s decision-making process (Franze and An- derson, 2015; Kearney and Merrill, 2000). The con- tent of these briefs reveals explicit attempts to per- suade justices and provides a fascinating setting for empirical study of influence through language. As such, we take the perspective of an amicus, propos- ing a probabilistic model of the various parties to a case that accounts for the amicus’ goals. Our model of SCOTUS is considerably more comprehensive than past work in political science, which has focused primarily on ideal point models that use votes as evidence. Text has been incorpo- rated more recently as a way of making such models more interpretable, but without changing the funda- mental assumptions (Lauderdale and Clark, 2014). Here, we draw on decision theory to posit amici as rational agents. We assume these amici-agents max- imize their expected utility by framing their argu- ments to sway justices towards favorable outcomes. We build …

Content truncated to 500 words