Conversational Flow in Oxford-style Debates

Proceedings of NAACL-HLT 2016, pages 136–141, San Diego, California, June 12-17, 2016. c⃝2016 Association for Computational Linguistics Conversational Flow in Oxford-style Debates Justine Zhang,1 Ravi Kumar,2 Sujith Ravi,2 Cristian Danescu-Niculescu-Mizil1 1Cornell University, 2Google jz727@cornell.edu, ravi.k53@gmail.com, ravi.sujith@gmail.com, cristian@cs.cornell.edu Abstract Public debates are a common platform for pre- senting and juxtaposing diverging views on important issues. In this work we propose a methodology for tracking how ideas flow be- tween participants throughout a debate. We use this approach in a case study of Oxford- style debates—a competitive format where the winner is determined by audience votes—and show how the outcome of a debate depends on aspects of conversational flow. In particu- lar, we find that winners tend to make better use of a debate’s interactive component than losers, by actively pursuing their opponents’ points rather than promoting their own ideas over the course of the conversation. 1 Introduction Public debates are a common platform for present- ing and juxtaposing diverging viewpoints. As op- posed to monologues where speakers are limited to expressing their own beliefs, debates allow for participants to interactively attack their opponents’ points while defending their own. The resulting flow of ideas is a key feature of this conversation genre. In this work we introduce a computational frame- work for characterizing debates in terms of conver- sational flow. This framework captures two main de- bating strategies—promoting one’s own points and attacking the opponents’ points—and tracks their relative usage throughout the debate. By applying this methodology to a setting where debate winners are known, we show that conversational flow pat- terns are predictive of which debater is more likely to persuade an audience. Case study: Oxford-style debates. Oxford-style debates provide a setting that is particularly conve- nient for studying the effects of conversational flow. In this competitive debate format, two teams argue for or against a preset motion in order to persuade a live audience to take their position. The audience votes before and after the debate, and the winning team is the one that sways more of the audience to- wards its view. This setup allows us to focus on the effects of conversational flow since it disentangles them from the audience’s prior leaning.1 The debate format involves an opening statement from the two sides, which presents an overview of their arguments before the discussion begins. This allows us to easily identify talking points held by the participants prior to the interaction, and con- sider them separately from points introduced spon- taneously to serve the discussion. This work is taking steps towards better model- ing of conversational dynamics, by: (i) introducing a debate dataset with rich metadata (Section 2), (ii) proposing a framework for tracking the flow of ideas (Section 3), and (iii) showing its effectiveness in a predictive setting (Section 4). 2 Debate Dataset: Intelligence Squared In this study we use transcripts and results of Oxford-style debates from the public debate series “Intelligence Squared Debates” (IQ2 for short).2 These debates are recorded live, and contain mo- tions covering a …

Content truncated to 500 words