Separating Polarization from Noise: Comparison and Normalization of Structural Polarization Measures

Quantifying the amount of polarization is crucial for understanding and studying political polarization in political and social systems. Several methods are used commonly to measure polarization in social networks by purely inspecting their structure. We analyse eight of such methods and show that all of them yield high polarization scores even for random networks with similar density and degree distributions to typical real-world networks. Further, some of the methods are sensitive to degree distributions and relative sizes of the polarized groups. We propose normalization to the existing scores and a minimal set of tests that a score should pass in order for it to be suitable for separating polarized networks from random noise. The performance of the scores increased by 38%-220% after normalization in a classification task of 203 networks. Further, we find that the choice of method is not as important as normalization, after which most of the methods have better performance than the best-performing method before normalization. This work opens up the possibility to critically assess and compare the features and performance of different methods for measuring structural polarization.

[1]  Igor M. Sokolov,et al.  Modeling echo chambers and polarization dynamics in social networks , 2019, Physical review letters.

[2]  Justin H. Gross,et al.  Measurement and theory in legislative networks: The evolving topology of Congressional collaboration , 2014, Soc. Networks.

[3]  Bryan C. Semaan,et al.  Social Media Is Polarized, Social Media Is Polarized: Towards a New Design Agenda for Mitigating Polarization , 2018, Conference on Designing Interactive Systems.

[4]  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.

[5]  Manfred Schoch,et al.  Quantification of echo Chambers: a Methodological Framework considering Multi-Party Systems , 2019, ECIS.

[6]  A. J. Morales,et al.  Measuring Political Polarization: Twitter shows the two sides of Venezuela , 2015, Chaos.

[7]  L. Akoglu Quantifying Political Polarity Based on Bipartite Opinion Networks , 2014, ICWSM.

[8]  Venkata Rama Kiran Garimella,et al.  Secular vs. Islamist polarization in Egypt on Twitter , 2013, 2013 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM 2013).

[9]  Chiara Orsini,et al.  Quantifying randomness in real networks , 2015, Nature Communications.

[10]  Robert N. Stern,et al.  Informal Networks and Organizational Crises: An Experimental Simulation , 1988 .

[11]  Bruce A. Reed,et al.  A Critical Point for Random Graphs with a Given Degree Sequence , 1995, Random Struct. Algorithms.

[12]  Colin McDiarmid,et al.  Modularity of regular and treelike graphs , 2018, J. Complex Networks.

[13]  Zachary P. Neal,et al.  A sign of the times? Weak and strong polarization in the U.S. Congress, 1973-2016 , 2020, Soc. Networks.

[14]  E. Hargittai,et al.  Cross-ideological discussions among conservative and liberal bloggers , 2007 .

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

[16]  Priya Mahadevan,et al.  Systematic topology analysis and generation using degree correlations , 2006, SIGCOMM.

[17]  ANDRES REILJAN,et al.  ‘Fear and loathing across party lines’ (also) in Europe: Affective polarisation in European party systems , 2019, European Journal of Political Research.

[18]  Shiliang Sun,et al.  A review of natural language processing techniques for opinion mining systems , 2017, Inf. Fusion.

[19]  Tiago P Peixoto,et al.  Parsimonious module inference in large networks. , 2012, Physical review letters.

[20]  Mark E. J. Newman,et al.  Power-Law Distributions in Empirical Data , 2007, SIAM Rev..

[21]  Aristides Gionis,et al.  Political Discourse on Social Media: Echo Chambers, Gatekeepers, and the Price of Bipartisanship , 2018, WWW.

[22]  D. Collier,et al.  Measurement Validity: A Shared Standard for Qualitative and Quantitative Research , 2001, American Political Science Review.

[23]  David Chavalarias,et al.  Reconstruction of the socio-semantic dynamics of political activist Twitter networks—Method and application to the 2017 French presidential election , 2018, PloS one.

[24]  James P. Bagrow,et al.  Communities and bottlenecks: trees and treelike networks have high modularity. , 2012, Physical review. E, Statistical, nonlinear, and soft matter physics.

[25]  John H. Evans,et al.  Have American's Social Attitudes Become More Polarized? , 1996, American Journal of Sociology.

[26]  Michelangelo Puliga,et al.  Voting Behavior, Coalitions and Government Strength through a Complex Network Analysis , 2014, PloS one.

[27]  Kathryn B. Laskey,et al.  Stochastic blockmodels: First steps , 1983 .

[28]  Yasushi Kawase,et al.  Z-Score-Based Modularity for Community Detection in Networks , 2015, PloS one.

[29]  Joel Nishimura,et al.  Configuring Random Graph Models with Fixed Degree Sequences , 2016, SIAM Rev..

[30]  James Zou,et al.  Analyzing Polarization in Social Media: Method and Application to Tweets on 21 Mass Shootings , 2019, NAACL.

[31]  Ted Hsuan Yun Chen,et al.  Separating Controversy from Noise: Comparison and Normalization of Structural Polarization Measures , 2021, ArXiv.

[32]  Kareem Darwish,et al.  Quantifying Polarization on Twitter: The Kavanaugh Nomination , 2019, SocInfo.

[33]  R. Guimerà,et al.  Modularity from fluctuations in random graphs and complex networks. , 2004, Physical review. E, Statistical, nonlinear, and soft matter physics.

[34]  Yilin Zhang,et al.  Understanding Regularized Spectral Clustering via Graph Conductance , 2018, NeurIPS.

[35]  Jacob Ratkiewicz,et al.  Political Polarization on Twitter , 2011, ICWSM.

[36]  Taylor W. Brown,et al.  Exposure to opposing views on social media can increase political polarization , 2018, Proceedings of the National Academy of Sciences.

[37]  Claire Cardie,et al.  A Measure of Polarization on Social Media Networks Based on Community Boundaries , 2013, ICWSM.

[38]  1959 , 2018, Documents on Irish Foreign Policy vol. XI.

[39]  Clara Pizzuti,et al.  Analyzing Voting Behavior in Italian Parliament: Group Cohesion and Evolution , 2012, 2012 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining.

[40]  Mir Saman Tajbakhsh,et al.  A framework for quantifying controversy of social network debates using attributed networks: biased random walk (BRW) , 2020, Social Network Analysis and Mining.

[41]  Colin McDiarmid,et al.  Modularity of Erdős‐Rényi random graphs , 2018, AofA.

[42]  Domenico Talia,et al.  Learning Political Polarization on Social Media Using Neural Networks , 2020, IEEE Access.

[43]  A. Gelman,et al.  Partisans without Constraint: Political Polarization and Trends in American Public Opinion. , 2008, AJS; American journal of sociology.

[44]  Aristides Gionis,et al.  Quantifying Controversy on Social Media , 2018, ACM Trans. Soc. Comput..

[45]  Mikko Kivelä,et al.  Polarization of Climate Politics Results from Partisan Sorting: Evidence from Finnish Twittersphere , 2020, Global Environmental Change.

[46]  F. Radicchi,et al.  Statistical significance of communities in networks. , 2009, Physical review. E, Statistical, nonlinear, and soft matter physics.

[47]  Mucahid Kutlu,et al.  Embeddings-Based Clustering for Target Specific Stances: The Case of a Polarized Turkey , 2020, ArXiv.

[48]  Jennifer McCoy,et al.  Polarization and the Global Crisis of Democracy: Common Patterns, Dynamics, and Pernicious Consequences for Democratic Polities , 2018 .

[49]  Brian W. Kernighan,et al.  An efficient heuristic procedure for partitioning graphs , 1970, Bell Syst. Tech. J..

[50]  Lilliana Mason,et al.  “I Disrespectfully Agree”: The Differential Effects of Partisan Sorting on Social and Issue Polarization , 2015 .

[51]  Cristopher Moore,et al.  Scalable detection of statistically significant communities and hierarchies, using message passing for modularity , 2014, Proceedings of the National Academy of Sciences.

[52]  Santo Fortunato,et al.  Community detection in networks: A user guide , 2016, ArXiv.

[53]  Kyriaki Kalimeri,et al.  Falling into the Echo Chamber: the Italian Vaccination Debate on Twitter , 2020, ICWSM.

[54]  Mahmoud Al-Ayyoub,et al.  Measuring the controversy level of Arabic trending topics on Twitter , 2016, 2016 7th International Conference on Information and Communication Systems (ICICS).

[55]  Romualdo Pastor-Satorras,et al.  Quantifying echo chamber effects in information spreading over political communication networks , 2019, EPJ Data Science.

[56]  S. Fortunato,et al.  Resolution limit in community detection , 2006, Proceedings of the National Academy of Sciences.

[57]  Jonathan Bright,et al.  Explaining the Emergence of Political Fragmentation on Social Media: The Role of Ideology and Extremism , 2018, J. Comput. Mediat. Commun..

[58]  Albert,et al.  Emergence of scaling in random networks , 1999, Science.

[59]  Dario Fasino,et al.  Generating large scale-free networks with the Chung-Lu random graph model , 2019, ArXiv.

[60]  M. Fiorina,et al.  Political Polarization in the American Public , 2008 .

[61]  David R. Jones Party Polarization and Legislative Gridlock , 2001 .

[62]  G. Zollo,et al.  The impact of group polarization on the quality of online debate in social media: A systematic literature review , 2021 .

[63]  Lorien Jasny,et al.  An empirical examination of echo chambers in US climate policy networks , 2015 .

[64]  Taro Takaguchi,et al.  Randomized reference models for temporal networks , 2018, SIAM Rev..

[65]  Marco Brambilla,et al.  Measuring Controversy in Social Networks Through NLP , 2020, SPIRE.

[66]  姜寅求 1970 , 1970, Literatur in der SBZ/DDR.

[67]  Anna Rumshisky,et al.  Combining Network and Language Indicators for Tracking Conflict Intensity , 2017, SocInfo.

[68]  S. Levin,et al.  The dynamics of political polarization , 2021, Proceedings of the National Academy of Sciences.

[69]  Alan M. Frieze,et al.  Random graphs , 2006, SODA '06.

[70]  Vipin Kumar,et al.  A Fast and High Quality Multilevel Scheme for Partitioning Irregular Graphs , 1998, SIAM J. Sci. Comput..

[71]  Bryan C. Semaan,et al.  (Re)Design to Mitigate Political Polarization , 2019, Proc. ACM Hum. Comput. Interact..

[72]  Ridi Ferdiana,et al.  A Review of Sentiment Analysis for Non-English Language , 2019, 2019 International Conference of Artificial Intelligence and Information Technology (ICAIIT).

[73]  Venkata Rama Kiran Garimella Polarization on Social Media , 2018 .

[74]  A. Maritan,et al.  True scale-free networks hidden by finite size effects , 2020, Proceedings of the National Academy of Sciences.

[75]  C. Makridis,et al.  The Real Cost of Political Polarization: Evidence from the COVID-19 Pandemic , 2020, SSRN Electronic Journal.