Winning on the Merits: The Joint Effects of Content and Style on Debate Outcomes

Debate and deliberation play essential roles in politics and government, but most models presume that debates are won mainly via superior style or agenda control. Ideally, however, debates would be won on the merits, as a function of which side has the stronger arguments. We propose a predictive model of debate that estimates the effects of linguistic features and the latent persuasive strengths of different topics, as well as the interactions between the two. Using a dataset of 118 Oxford-style debates, our model’s combination of content (as latent topics) and style (as linguistic features) allows us to predict audience-adjudicated winners with 74% accuracy, significantly outperforming linguistic features alone (66%). Our model finds that winning sides employ stronger arguments, and allows us to identify the linguistic features associated with strong or weak arguments.

[1]  Matt Thomas,et al.  Get out the vote: Determining support or opposition from Congressional floor-debate transcripts , 2006, EMNLP.

[2]  Vincent Ng,et al.  Why are You Taking this Stance? Identifying and Classifying Reasons in Ideological Debates , 2014, EMNLP.

[3]  Philip Pettit,et al.  The good polity : normative analysis of the state , 1991 .

[4]  Amy Beth Warriner,et al.  Norms of valence, arousal, and dominance for 13,915 English lemmas , 2013, Behavior Research Methods.

[5]  Marie-Francine Moens,et al.  Argumentation mining , 2011, Artificial Intelligence and Law.

[6]  Owen Rambow,et al.  Identifying Justifications in Written Dialogs by Classifying Text as Argumentative , 2011, Int. J. Semantic Comput..

[7]  John Rawlst,et al.  The Idea of Public Reason Revisited , 1997 .

[8]  K. Hyland,et al.  Metadiscourse: Exploring Interaction in Writing , 2005 .

[9]  Philip Resnik,et al.  Modeling topic control to detect influence in conversations using nonparametric topic models , 2014, Machine Learning.

[10]  C. List,et al.  Social Choice Theory and Deliberative Democracy: A Reconciliation , 2002, British Journal of Political Science.

[11]  Saif Mohammad,et al.  CROWDSOURCING A WORD–EMOTION ASSOCIATION LEXICON , 2013, Comput. Intell..

[12]  J. T. Irvine.  Formality and Informality in Communicative Events , 1979 .

[13]  Marie-Francine Moens,et al.  Automatic detection of arguments in legal texts , 2007, ICAIL.

[14]  Michael Röder,et al.  Exploring the Space of Topic Coherence Measures , 2015, WSDM.

[15]  Ming-Wei Chang,et al.  Discriminative Learning over Constrained Latent Representations , 2010, NAACL.

[16]  Joshua Cohen,et al.  DELIBERATION AND DEMOCRATIC LEGITIMACY , 2005, Philosophy, Politics, Democracy.

[17]  Tong Wang,et al.  Automatic Acquisition of Lexical Formality , 2010, COLING.

[18]  Michal Rosen-Zvi,et al.  Hidden Topic Markov Models , 2007, AISTATS.

[19]  Chris Reed,et al.  Modelling argument recognition and reconstruction , 2008 .

[20]  Dan Goldwasser,et al.  “I Object!” Modeling Latent Pragmatic Effects in Courtroom Dialogues , 2014, EACL.

[21]  Philip Resnik,et al.  Real-Time Reactions to a 2012 Presidential Debate A Method for Understanding Which Messages Matter , 2014 .

[22]  F. C. P. Motta.  The theory of communicative action , 1991 .

[23]  C. Sunstein.  The Law of Group Polarization , 1999, How Change Happens.

[24]  Cristian Danescu-Niculescu-Mizil,et al.  Winning Arguments: Interaction Dynamics and Persuasion Strategies in Good-faith Online Discussions , 2016, WWW.

[25]  Claire Cardie,et al.  A Piece of My Mind: A Sentiment Analysis Approach for Online Dispute Detection , 2014, ACL.

[26]  J. Druckman.  The Decline of the Death Penalty and the Discovery of Innocence , 2008 .

[27]  Jonathan T. Morgan,et al.  Annotating Social Acts: Authority Claims and Alignment Moves in Wikipedia Talk Pages , 2011 .

[28]  M. A. Britt,et al.  The Effects of Hedges in Persuasive Arguments , 2008 .

[29]  Livio Robaldo,et al.  The Penn Discourse Treebank 2.0 Annotation Manual , 2007 .

[30]  Dan Klein,et al.  Accurate Unlexicalized Parsing , 2003, ACL.

[31]  Graeme Hirst,et al.  Classifying arguments by scheme , 2011, ACL.

[32]  Claire Cardie,et al.  Improving Agreement and Disagreement Identification in Online Discussions with A Socially-Tuned Sentiment Lexicon , 2014, WASSA@ACL.

[33]  Noah A. Smith,et al.  The Media Frames Corpus: Annotations of Frames Across Issues , 2015, ACL.

[34]  Fiona Browne,et al.  Applying Kernel Methods to Argumentation Mining , 2012, FLAIRS.

[35]  Thorsten Joachims,et al.  Learning structural SVMs with latent variables , 2009, ICML '09.

[36]  Christopher Potts,et al.  Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank , 2013, EMNLP.

[37]  Noah A. Smith,et al.  Frame-Semantic Parsing , 2014, CL.

[38]  Maria Leonor Pacheco,et al.  of the Association for Computational Linguistics: , 2001 .

[39]  Janyce Wiebe,et al.  Recognizing Contextual Polarity in Phrase-Level Sentiment Analysis , 2005, HLT.

[40]  Jane J. Mansbridge.  Rethinking Representation , 2003, American Political Science Review.

[41]  C. Fillmore.  FRAME SEMANTICS AND THE NATURE OF LANGUAGE * , 1976 .

[42]  M. McCombs.  A Look at Agenda-setting: past, present and future , 2005 .

[43]  Philip Resnik,et al.  Tea Party in the House: A Hierarchical Ideal Point Topic Model and Its Application to Republican Legislators in the 112th Congress , 2015, ACL.

[44]  Owen Rambow,et al.  Staying on Topic: An Indicator of Power in Political Debates , 2014, EMNLP.

[45]  Ralf D. Brown,et al.  THE PRONOUNS OF POWER AND SOLIDARITY , 1968 .

[46]  Herbert W. Simons,et al.  Persuasion in Society , 2011 .

[47]  James N. Druckman,et al.  The Decline of the Death Penalty and the Discovery of Innocence , 2008 .

[48]  E. Noelle-Neumann.  The Spiral of Silence A Theory of Public Opinion , 1974 .

[49]  Marie-Francine Moens,et al.  Argumentation mining: the detection, classification and structure of arguments in text , 2009, ICAIL.

[50]  Daniel Marcu,et al.  Evaluating Multiple Aspects of Coherence in Student Essays , 2004, NAACL.

[51]  John-Charles Wilson.  Politically Speaking: The Pragmatic Analysis of Political Language , 1990 .

[52]  David Lazer,et al.  A Frame of Mind: Using Statistical Models for Detection of Framing and Agenda Setting Campaigns , 2015, ACL.

[53]  Cristian Danescu-Niculescu-Mizil,et al.  Conversational Flow in Oxford-style Debates , 2016, NAACL.

[54]  Amy Beth Warriner,et al.  Concreteness ratings for 40 thousand generally known English word lemmas , 2014, Behavior research methods.

[55]  Yulan He,et al.  A Study of the Impact of Persuasive Argumentation in Political Debates , 2016, NAACL.

[56]  Vincent Ng,et al.  Modeling Argument Strength in Student Essays , 2015, ACL.

[57]  Iryna Gurevych,et al.  Identifying Argumentative Discourse Structures in Persuasive Essays , 2014, EMNLP.

[58]  Philip Resnik,et al.  More than Words: Syntactic Packaging and Implicit Sentiment , 2009, NAACL.