Disunited Nations? A Multiplex Network Approach to Detecting Preference Affinity Blocs using Texts and Votes

This paper contributes to an emerging literature that models votes and text in tandem to better understand polarization of expressed preferences. It introduces a new approach to estimate preference polarization in multidimensional settings, such as international relations, based on developments in the natural language processing and network science literatures -- namely word embeddings, which retain valuable syntactical qualities of human language, and community detection in multilayer networks, which locates densely connected actors across multiple, complex networks. We find that the employment of these tools in tandem helps to better estimate states' foreign policy preferences expressed in UN votes and speeches beyond that permitted by votes alone. The utility of these located affinity blocs is demonstrated through an application to conflict onset in International Relations, though these tools will be of interest to all scholars faced with the measurement of preferences and polarization in multidimensional settings.

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

[2]  Bruce A. Desmarais,et al.  Temporal Exponential Random Graph Models with btergm: Estimation and Bootstrap Confidence Intervals , 2018 .

[3]  Bruce A. Desmarais,et al.  Statistical Mechanics of Networks: Estimation and Uncertainty Forthcoming: Physica A , 2012 .

[4]  K. T. Poole,et al.  Polarized America: The Dance of Ideology and Unequal Riches , 2006 .

[5]  S. Pauls,et al.  Affinity communities in United Nations voting: Implications for democracy, cooperation, and conflict , 2017 .

[6]  N. Christakis,et al.  The Spread of Obesity in a Large Social Network Over 32 Years , 2007, The New England journal of medicine.

[7]  Michael A. Bailey,et al.  Estimating Dynamic State Preferences from United Nations Voting Data , 2015 .

[8]  M. Newman.  Analysis of weighted networks. , 2004, Physical review. E, Statistical, nonlinear, and soft matter physics.

[9]  Stephen P. Nicholson,et al.  Partisans in Robes: Party Cues and Public Acceptance of Supreme Court Decisions , 2014 .

[10]  P. Mucha,et al.  Party Polarization in Congress: A Social Networks Approach , 2009, 0907.3509.

[11]  Tom S. Clark,et al.  Scaling Politically Meaningful Dimensions Using Texts and Votes , 2014 .

[12]  Slava J. Mikhaylov,et al.  Understanding state preferences with text as data: Introducing the UN General Debate corpus , 2017, ArXiv.

[13]  Kenneth Benoit,et al.  Estimating Intra-Party Preferences: Comparing Speeches to Votes* , 2015, Political Science Research and Methods.

[14]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[15]  Matt J. Kusner,et al.  Supervised Word Mover's Distance , 2016, NIPS.

[16]  Patrick Pantel,et al.  From Frequency to Meaning: Vector Space Models of Semantics , 2010, J. Artif. Intell. Res..

[17]  V. Traag,et al.  Trading Communities, the Networked Structure of International Relations, and the Kantian Peace , 2012 .

[18]  Amanda L. Traud,et al.  Community Structure in Congressional Cosponsorship Networks , 2007, 0708.1191.

[19]  E. Voeten,et al.  Precedent in International Courts: A Network Analysis of Case Citations by the European Court of Human Rights , 2011, British Journal of Political Science.

[20]  Zuhair Bandar,et al.  Sentence similarity based on semantic nets and corpus statistics , 2006, IEEE Transactions on Knowledge and Data Engineering.

[21]  M E J Newman,et al.  Modularity and community structure in networks. , 2006, Proceedings of the National Academy of Sciences of the United States of America.

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

[23]  Vito D'Orazio,et al.  The MID4 dataset, 2002–2010: Procedures, coding rules and description , 2015 .

[24]  E. Bullmore,et al.  A Resilient, Low-Frequency, Small-World Human Brain Functional Network with Highly Connected Association Cortical Hubs , 2006, The Journal of Neuroscience.

[25]  Mason A. Porter,et al.  Multilayer networks , 2013, J. Complex Networks.

[26]  Boleslaw K. Szymanski,et al.  Threshold-limited spreading in social networks with multiple initiators , 2013, Scientific Reports.

[27]  Carlo Strapparava,et al.  Corpus-based and Knowledge-based Measures of Text Semantic Similarity , 2006, AAAI.

[28]  Erik Gartzke,et al.  Kant We All Just get Along? Opportunity, Willingness, and the Origins of the Democratic Peace , 1998 .

[29]  Peter J. Mucha,et al.  Portrait of Political Party Polarization1 , 2013, Network Science.

[30]  Bruce A. Desmarais,et al.  Inferential Network Analysis with Exponential Random Graph Models , 2011, Political Analysis.

[31]  Mason A. Porter,et al.  Community Structure in the United Nations General Assembly , 2010, ArXiv.

[32]  Paul Heinbecker,et al.  Politics and Process at the United Nations: The Global Dance@@@Irrelevant or Indispensable: The United Nations in the 21st Century@@@Adapting the United Nations to a Postmodern Era , 2005 .

[33]  Matt J. Kusner,et al.  From Word Embeddings To Document Distances , 2015, ICML.

[34]  Stijn van Dongen,et al.  Construction, Visualisation, and Clustering of Transcription Networks from Microarray Expression Data , 2007, PLoS Comput. Biol..

[35]  Christopher D. Manning,et al.  Random Walks for Text Semantic Similarity , 2009, Graph-based Methods for Natural Language Processing.

[36]  E. Voeten.  Clashes in the Assembly , 2000, International Organization.

[37]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

[38]  E. Voeten.  Data and analyses of voting in the United Nations General Assembly , 2013 .

[39]  Jonathan B. Slapin,et al.  Position Taking in European Parliament Speeches , 2010 .

[40]  Alessandro Lenci,et al.  Distributional Models of Word Meaning , 2018 .

[41]  Bruce Bueno de Mesquita,et al.  Measuring Systemic Polarity , 1975 .

[42]  Andrew B. Nobel,et al.  Community Extraction in Multilayer Networks with Heterogeneous Community Structure , 2016, J. Mach. Learn. Res..

[43]  Marc Ratkovic,et al.  Estimating Spatial Preferences from Votes and Text , 2018, Political Analysis.

[44]  M. Laver,et al.  Extracting Policy Positions from Political Texts Using Words as Data , 2003, American Political Science Review.