A Study of the Impact of Persuasive Argumentation in Political Debates

Proceedings of NAACL-HLT 2016, pages 1405–1413, San Diego, California, June 12-17, 2016. c⃝2016 Association for Computational Linguistics A Study of the Impact of Persuasive Argumentation in Political Debates Amparo Elizabeth Cano-Basave and Yulan He Aston University, UK a.cano-basave@aston.ac.uk,y.he@cantab.net Abstract Persuasive communication is the process of shaping, reinforcing and changing others’ re- sponses. In political debates, speakers ex- press their views towards the debated topics by choosing both the content of their discourse and the argumentation process. In this work we study the use of semantic frames for mod- elling argumentation in speakers’ discourse. We investigate the impact of a speaker’s argu- mentation style and their effect in influencing an audience in supporting their candidature. We model the influence index of each candi- date based on their relative standings in the polls released prior to the debate and present a system which ranks speakers in terms of their relative influence using a combination of content and persuasive argumentation fea- tures. Our results show that although con- tent alone is predictive of a speaker’s influ- ence rank, persuasive argumentation also af- fects such indices. 1 Introduction In recent years, researchers have studied politi- cal texts detecting ideological positions (Sim et al., 2013; Hasan and Ng, 2013), predicting vot- ing patterns (Thomas et al., 2006; Gerrish and Blei, 2011) and characterising power based on lin- guistic features (Prabhakaran et al., 2013). While there is a vast amount of theoretical research on the rhetoric of politicians, only recently there has been a growing interest in understanding the argumenta- tion processes involved in political communication by means of computational linguistics (Hasan and Ng, 2013; Boltuˇzi´c and ˇSnajder, 2014). During a debate, a speaker tries to convince the audience of a particular point of view. This nor- mally involves an argumentation process, where the structuring of ideas is built upon logical connections between claims and premises, and a persuasive com- munication style. In this paper, we study the impact of persuasive argumentation in political debates on candidates’ power/influence ranking. As opposed to previous approaches, we propose to characterise political debates based on persuasive argumentation modelled through semantic frames. Previous work (Rosenberg and Hirschberg, 2009) has analysed political speech transcripts identify- ing prosodic and lexical-syntactic cues which cor- relate with political personalities. Prabhakaran et al. (2013) proposed interactions within political de- bates as predictors of a candidate’s relative power or influence rank in polls. More recently they also found topic-shifting to be a good indicator of candi- date’s relative rankings in polls (Prabhakaran et al., 2014). Argumentation in debates has been studied from the perspective of automatic argument extrac- tion (Cabrio and Villata, 2012) and stance classifi- cation (Hasan and Ng, 2013). However, to the best of our knowledge, argumentation has not been ex- plored as a influence rank indicator. Moreover the study of persuasion in the NLP community has been so far limited. The novelty of our work is the proposal of a method to automatically extract persuasive argu- mentation features from political debates by means …

Content truncated to 500 words