On the Complexity of Opinions and Online Discussions

In an increasingly polarized world, demagogues who reduce complexity down to simple arguments based on emotion are gaining in popularity. Are opinions and online discussions falling into demagoguery? In this work, we aim to provide computational tools to investigate this question and, by doing so, explore the nature and complexity of online discussions and their space of opinions, uncovering where each participant lies. More specifically, we present a modeling framework to construct latent representations of opinions in online discussions which are consistent with human judgments, as measured by online voting. If two opinions are close in the resulting latent space of opinions, it is because humans think they are similar. Our framework is theoretically grounded and establishes a surprising connection between opinion and voting models and the sign-rank of matrices. Moreover, it also provides a set of practical algorithms to both estimate the dimensionality of the latent space of opinions and infer where opinions expressed by the participants of an online discussion lie in this space. Experiments on a large dataset from Yahoo! News, Yahoo! Finance, Yahoo! Sports, and the Newsroom app show that many discussions are multisided, reveal a positive correlation between the complexity of a discussion, its linguistic diversity and its level of controversy, and show that our framework may be able to circumvent language nuances such as sarcasm or humor by relying on human judgments instead of textual analysis.

[1]  Lei Zhang,et al.  Sentiment Analysis and Opinion Mining , 2017, Encyclopedia of Machine Learning and Data Mining.

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

[3]  Robert Tibshirani,et al.  Spectral Regularization Algorithms for Learning Large Incomplete Matrices , 2010, J. Mach. Learn. Res..

[4]  Rupak Majumdar,et al.  Tools and Algorithms for the Construction and Analysis of Systems , 1997, Lecture Notes in Computer Science.

[5]  Noga Alon,et al.  Sign rank versus VC dimension , 2015, COLT.

[6]  R. Axelrod.  The Dissemination of Culture , 1997 .

[7]  Vojtech Rödl,et al.  Geometrical realization of set systems and probabilistic communication complexity , 1985, 26th Annual Symposium on Foundations of Computer Science (sfcs 1985).

[8]  James M. Enelow,et al.  The Spatial Theory of Voting: An Introduction , 1984 .

[9]  James Bennett,et al.  The Netflix Prize , 2007 .

[10]  Hoon Pyo Hong.  Comparison of Several Decision Algorithms for the Existential Theory of the Reals , 1991 .

[11]  Jure Leskovec,et al.  Signed networks in social media , 2010, CHI.

[12]  M. Newman,et al.  Nonequilibrium phase transition in the coevolution of networks and opinions. , 2006, Physical review. E, Statistical, nonlinear, and soft matter physics.

[13]  Jürgen Broß,et al.  Aspect-Oriented Sentiment Analysis of Customer Reviews Using Distant Supervision Techniques , 2013 .

[14]  Yoon Kim,et al.  Convolutional Neural Networks for Sentence Classification , 2014, EMNLP.

[15]  Greg Linden,et al.  Amazon . com Recommendations Item-to-Item Collaborative Filtering , 2001 .

[16]  Troy Lee,et al.  An Approximation Algorithm for Approximation Rank , 2008, 2009 24th Annual IEEE Conference on Computational Complexity.

[17]  Jure Leskovec,et al.  Predicting positive and negative links in online social networks , 2010, WWW '10.

[18]  Navneet Kaur,et al.  Opinion mining and sentiment analysis , 2016, 2016 3rd International Conference on Computing for Sustainable Global Development (INDIACom).

[19]  Yehuda Koren,et al.  Advances in Collaborative Filtering , 2011, Recommender Systems Handbook.

[20]  G. Sacks.  A DECISION METHOD FOR ELEMENTARY ALGEBRA AND GEOMETRY , 2003 .

[21]  Adi Shraibman,et al.  Rank, Trace-Norm and Max-Norm , 2005, COLT.

[22]  Rabab Kreidieh Ward,et al.  Deep Sentence Embedding Using Long Short-Term Memory Networks: Analysis and Application to Information Retrieval , 2015, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[23]  Leonardo Mendonça de Moura,et al.  Solving non-linear arithmetic , 2012, ACCA.

[24]  Pablo Barberá.  Birds of the Same Feather Tweet Together: Bayesian Ideal Point Estimation Using Twitter Data , 2015, Political Analysis.

[25]  C. Rowley.  The Relevance of the Median Voter Theorem , 1984 .

[26]  Nikolaj Bjørner,et al.  Z3: An Efficient SMT Solver , 2008, TACAS.

[27]  Nick Cramer,et al.  Automatic Keyword Extraction from Individual Documents , 2010 .

[28]  Emo Welzl,et al.  Partition trees for triangle counting and other range searching problems , 1988, SCG '88.

[29]  Jacob Ratkiewicz,et al.  Predicting the Political Alignment of Twitter Users , 2011, 2011 IEEE Third Int'l Conference on Privacy, Security, Risk and Trust and 2011 IEEE Third Int'l Conference on Social Computing.

[30]  TibshiraniRobert,et al.  Spectral Regularization Algorithms for Learning Large Incomplete Matrices , 2010 .

[31]  Adel Javanmard,et al.  1-bit matrix completion under exact low-rank constraint , 2015, 2015 49th Annual Conference on Information Sciences and Systems (CISS).

[32]  Christopher Potts,et al.  Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank , 2013, EMNLP.

[33]  M. Degroot.  Reaching a Consensus , 1974 .

[34]  Amey Bhangale,et al.  The complexity of computing the minimum rank of a sign pattern matrix , 2015, ArXiv.

[35]  Jürgen Forster,et al.  A linear lower bound on the unbounded error probabilistic communication complexity , 2001, Proceedings 16th Annual IEEE Conference on Computational Complexity.

[36]  B. Grofman,et al.  A Unified Theory of Voting: Directional and Proximity Spatial Models , 1999 .

[37]  Inderjit S. Dhillon,et al.  Low rank modeling of signed networks , 2012, KDD.

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

[39]  Ronen Basri,et al.  Visibility constraints on features of 3D objects , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[40]  Amy X. Zhang,et al.  Controversy and Sentiment in Online News , 2014, ArXiv.

[41]  Niloy Ganguly,et al.  Learning and Forecasting Opinion Dynamics in Social Networks , 2015, NIPS.

[42]  Kevin P. Murphy,et al.  Machine learning - a probabilistic perspective , 2012, Adaptive computation and machine learning series.

[43]  Mehmet E. Yildiz,et al.  Binary Opinion Dynamics with Stubborn Agents , 2013, TEAC.

[44]  Rainer Hegselmann,et al.  Opinion dynamics and bounded confidence: models, analysis and simulation , 2002, J. Artif. Soc. Soc. Simul..

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

[46]  Niloy Ganguly,et al.  Learning a Linear Influence Model from Transient Opinion Dynamics , 2014, CIKM.

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

[48]  Mehmet E. Yildiz,et al.  Voting models in random networks , 2010, 2010 Information Theory and Applications Workshop (ITA).

[49]  Sung-Hyon Myaeng,et al.  Identifying Controversial Issues and Their Sub-topics in News Articles , 2010, PAISI.

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

[51]  Janos Simon,et al.  Probabilistic Communication Complexity , 1986, J. Comput. Syst. Sci..