GPolS: A Contextual Graph-Based Language Model for Analyzing Parliamentary Debates and Political Cohesion

Parliamentary debates present a valuable language resource for analyzing comprehensive options in electing representatives under a functional, free society. However, the esoteric nature of political speech coupled with non-linguistic aspects such as political cohesion between party members presents a complex and underexplored task of contextual parliamentary debate analysis. We introduce GPolS, a neural model for political speech stance analysis jointly exploiting both semantic language representations and relations between debate transcripts, motions, and political party members. Through experiments on real-world English data, we provide a use case of GPolS as a tool for political speech analysis and polarity prediction.

[1]  Sara Tonelli,et al.  Agreement and Disagreement: Comparison of Points of View in the Political Domain , 2016, COLING.

[2]  Janyce Wiebe,et al.  Tracking Point of View in Narrative , 1994, Comput. Linguistics.

[3]  Frank Hutter,et al.  Decoupled Weight Decay Regularization , 2017, ICLR.

[4]  Katarzyna Budzynska,et al.  A Deep Modular RNN Approach for Ethos Mining , 2018, IJCAI.

[5]  Arman Cohan,et al.  Longformer: The Long-Document Transformer , 2020, ArXiv.

[6]  Stephen Marshall,et al.  Activation Functions: Comparison of trends in Practice and Research for Deep Learning , 2018, ArXiv.

[7]  Stefan Bode,et al.  Demystifying “free will”: The role of contextual information and evidence accumulation for predictive brain activity , 2014, Neuroscience & Biobehavioral Reviews.

[8]  Martha L. Cottam.  Introduction to Political Psychology , 2004 .

[9]  Vincent Ng,et al.  Stance Classification of Ideological Debates: Data, Models, Features, and Constraints , 2013, IJCNLP.

[10]  Benno Stein,et al.  Exploiting Personal Characteristics of Debaters for Predicting Persuasiveness , 2020, ACL.

[11]  R. Hayton.  Reconstructing Conservatism?: The Conservative party in opposition, 1997–2010 , 2012 .

[12]  Yi Li,et al.  Opinion-aware Knowledge Graph for Political Ideology Detection , 2017, IJCAI.

[13]  S. Frid-Nielsen.  Human rights or security? Positions on asylum in European Parliament speeches , 2018 .

[14]  Yongdong Zhang,et al.  Semi-supervised User Profiling with Heterogeneous Graph Attention Networks , 2019, IJCAI.

[15]  S. Slembrouck.  The parliamentary Hansard ‘verbatim’ report: the written construction of spoken discourse , 1992 .

[16]  Riza Batista-Navarro,et al.  ParlVote: A Corpus for Sentiment Analysis of Political Debates , 2020, LREC.

[17]  Andrew L. Maas.  Rectifier Nonlinearities Improve Neural Network Acoustic Models , 2013 .

[18]  Noah A. Smith,et al.  Measuring Ideological Proportions in Political Speeches , 2013, EMNLP.

[19]  Robb Willer,et al.  The Social Structure of Political Echo Chambers: Variation in Ideological Homophily in Online Networks , 2017 .

[20]  Xuanjing Huang,et al.  How to Fine-Tune BERT for Text Classification? , 2019, CCL.

[21]  Will Lowe,et al.  Multilingual Sentiment Analysis: A New Approach to Measuring Conflict in Legislative Speeches , 2018, Legislative Studies Quarterly.

[22]  Martin Monahan.  Reconstructing Conservatism? The Conservative Party in Opposition, 1997–2010 by Richard Hayton. Manchester: Manchester University Press, 2012. 166pp., £60.00, ISBN 978 0 7190 8316 7 , 2014 .

[23]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[24]  L. Huddy,et al.  Group Identity and Political Cohesion , 2015 .

[25]  Markus Neuhäuser,et al.  Wilcoxon Signed Rank Test , 2006 .

[26]  D. Trilling.  Two Different Debates? Investigating the Relationship Between a Political Debate on TV and Simultaneous Comments on Twitter , 2015 .

[27]  Mariusz Dzieciatko,et al.  Application of Text Analytics to Analyze Emotions in the Speeches , 2018, ITIB.

[28]  Laura B. Stephenson,et al.  When the team’s jersey is what matters: Network analysis of party cohesion and structure in the Canadian House of Commons , 2018, Party Politics.

[29]  R'emi Louf,et al.  HuggingFace's Transformers: State-of-the-art Natural Language Processing , 2019, ArXiv.

[30]  Françoise Bouçek.  The structure and dynamics of intra‐party politics in Europe , 2002 .

[31]  Jeffrey Pennington,et al.  GloVe: Global Vectors for Word Representation , 2014, EMNLP.

[32]  Ludovic Rheault,et al.  Expressions of Anxiety in Political Texts , 2016, NLP+CSS@EMNLP.

[33]  Tomas Mikolov,et al.  Enriching Word Vectors with Subword Information , 2016, TACL.

[34]  Dan Goldwasser,et al.  Understanding the Language of Political Agreement and Disagreement in Legislative Texts , 2020, ACL.

[35]  Simone Paolo Ponzetto,et al.  Policy Preference Detection in Parliamentary Debate Motions , 2019, CoNLL.

[36]  Masoud Makrehchi,et al.  Detecting Agreement and Disagreement in Political Debates , 2018, SBP-BRiMS.

[37]  Helen Yannakoudakis,et al.  Abusive Language Detection with Graph Convolutional Networks , 2019, NAACL.

[38]  Vladimir Eidelman,et al.  How Predictable is Your State? Leveraging Lexical and Contextual Information for Predicting Legislative Floor Action at the State Level , 2018, COLING.

[39]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[40]  S. Utych.  Speaking style and candidate evaluations , 2019, Politics, Groups, and Identities.

[41]  Barbara Johnstone.  Stance, Style, and the Linguistic Individual , 2009 .

[42]  Claudio Gentile,et al.  Linear Hinge Loss and Average Margin , 1998, NIPS.

[43]  Keiichi Nakata,et al.  Towards Sentiment Analysis on Parliamentary Debates in Hansard , 2013, JIST.

[44]  Goran Glavas,et al.  Unsupervised Cross-Lingual Scaling of Political Texts , 2017, EACL.

[45]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[46]  David Vilares,et al.  Detecting Perspectives in Political Debates , 2017, EMNLP.

[47]  Pietro Liò,et al.  Graph Attention Networks , 2017, ICLR.

[48]  Riza Theresa Batista-Navarro,et al.  Identifying Opinion-Topics and Polarity of Parliamentary Debate Motions , 2018, WASSA@EMNLP.

[49]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[50]  Christopher Cochrane,et al.  Word Embeddings for the Analysis of Ideological Placement in Parliamentary Corpora , 2019, Political Analysis.

[51]  Riza Batista-Navarro,et al.  'Aye' or 'No'? Speech-level Sentiment Analysis of Hansard UK Parliamentary Debate Transcripts , 2018, LREC.

[52]  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.

[53]  Mohit Sharma,et al.  Analysis of Parliamentary Debate Transcripts Using Community-Based Graphical Approaches (Student Abstract) , 2020, AAAI.

[54]  Sanjeev Arora,et al.  An Exponential Learning Rate Schedule for Deep Learning , 2020, ICLR.

[55]  Serena Villata,et al.  Five Years of Argument Mining: a Data-driven Analysis , 2018, IJCAI.

[56]  S. Hug.  Selection Effects in Roll Call Votes , 2006, British Journal of Political Science.

[57]  Paolo Rosso,et al.  Stance polarity in political debates: A diachronic perspective of network homophily and conversations on Twitter , 2019, Data Knowl. Eng..

[58]  Jason Reifler,et al.  PARTY POLARIZATION IN AMERICAN POLITICS : Characteristics , Causes , and Consequences , 2013 .

[59]  Michael Sedlmair,et al.  More than Bags of Words: Sentiment Analysis with Word Embeddings , 2018 .

[60]  Riza Batista-Navarro,et al.  Sentiment and position-taking analysis of parliamentary debates: a systematic literature review , 2019, Journal of Computational Social Science.

[61]  D. Farrell,et al.  PARTY DISCIPLINE AND PARLIAMENTARY GOVERNMENT , 1999 .

[62]  Ramit Sawhney,et al.  Investigating Political Herd Mentality: A Community Sentiment Based Approach , 2019, ACL.

[63]  Murray Edelman,et al.  Political Language and Political Reality , 1985, PS: Political Science & Politics.

[64]  Serena Villata,et al.  DISPUTool - A tool for the Argumentative Analysis of Political Debates , 2019, IJCAI.

[65]  Jorge Nocedal,et al.  On the limited memory BFGS method for large scale optimization , 1989, Math. Program..

[66]  Carl W. Roberts,et al.  Text analysis for the social sciences : methods for drawing statistical inferences from texts and transcripts , 1997 .

[67]  Omer Levy,et al.  RoBERTa: A Robustly Optimized BERT Pretraining Approach , 2019, ArXiv.