Using Complex Argumentative Interactions to Reconstruct the Argumentative Structure of Large-Scale Debates

In this paper we consider the insights that can be gained by considering large scale argument networks and the complex interactions between their constituent propositions. We investigate metrics for analysing properties of these networks, illustrating these using a corpus of arguments taken from the 2016 US Presidential Debates. We present techniques for determining these features directly from natural language text and show that there is a strong correlation between these automatically identified features and the argumentative structure contained within the text. Finally, we combine these metrics with argument mining techniques and show how the identification of argumentative relations can be improved by considering the larger context in which they occur.

[1]  Trevor J. M. Bench-Capon,et al.  Semi-Automated Argumentative Analysis of Online Product Reviews , 2012, COMMA.

[2]  Rada Mihalcea,et al.  TextRank: Bringing Order into Text , 2004, EMNLP.

[3]  Bart Verheij,et al.  Handbook of Argumentation Theory , 1987 .

[4]  Chris Reed,et al.  Combining Argument Mining Techniques , 2015, ArgMining@HLT-NAACL.

[5]  J. R. Landis,et al.  The measurement of observer agreement for categorical data. , 1977, Biometrics.

[6]  Quoc V. Le,et al.  Distributed Representations of Sentences and Documents , 2014, ICML.

[7]  Jacob Cohen.  A Coefficient of Agreement for Nominal Scales , 1960 .

[8]  M. Stede,et al.  Argument Analytics , 2017 .

[9]  Chris Reed,et al.  Mining Arguments From 19th Century Philosophical Texts Using Topic Based Modelling , 2014, ArgMining@ACL.

[10]  Timothy Baldwin,et al.  An Empirical Evaluation of doc2vec with Practical Insights into Document Embedding Generation , 2016, Rep4NLP@ACL.

[11]  M. Randic,et al.  On Characterization of 3D Molecular Structure , 2002 .

[12]  Chris Reed,et al.  The CASS Technique for Evaluating the Performance of Argument Mining , 2016, ArgMining@ACL.

[13]  Benno Stein,et al.  “PageRank” for Argument Relevance , 2017, EACL.

[14]  George A. Miller,et al.  WordNet: A Lexical Database for English , 1995, HLT.

[15]  Sergey Brin,et al.  The Anatomy of a Large-Scale Hypertextual Web Search Engine , 1998, Comput. Networks.

[16]  Chris Reed,et al.  OVA+: an Argument Analysis Interface , 2014, COMMA.

[17]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[18]  Chris Reed,et al.  A Corpus of Argument Networks: Using Graph Properties to Analyse Divisive Issues , 2016, LREC.

[19]  Chris Reed,et al.  Building arguments with argumentation: the role of illocutionary force in computational models of argument , 2010, COMMA.

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

[21]  Reedchris,et al.  Towards an argument interchange format , 2006 .

[22]  Claire Cardie,et al.  Identifying Appropriate Support for Propositions in Online User Comments , 2014, ArgMining@ACL.

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

[24]  M. Kendall.  A NEW MEASURE OF RANK CORRELATION , 1938 .

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

[26]  Vangelis Karkaletsis,et al.  Identifying Argument Components through TextRank , 2016, ArgMining@ACL.