Distorting Political Communication: The Effect Of Hyperactive Users In Online Social Networks

Online Social Networks (OSNs) are used increasingly for political purposes. Among others, politicians externalize their views on issues, and users respond to them, initiating political discussions. Part of the discussions are shaped by hyperactive users. These are users that are over-proportionally active in relation to the mean. In this paper, we define the hyperactive user on the social media platform Facebook, both theoretically and mathematically. We apply a geometric topic modelling algorithm (GTM) on German political parties' posts and user comments to identify the topics discussed. We prove that hyperactive users have a significant role in the political discourse: They become opinion leaders, as well as set the content of discussions, thus creating an alternate picture of the public opinion. Given that, we discuss the dangers of replicating the specific bias by statistical and deep learning algorithms, which are used widely for recommendation systems and the profiling of OSN users.

[1]  Eitan Hersh.  Hacking the Electorate: How Campaigns Perceive Voters , 2015 .

[2]  Max Tegmark,et al.  Criticality in Formal Languages and Statistical Physics , 2016 .

[3]  Marco Conti,et al.  Structure of Ego-Alter Relationships of Politicians in Twitter , 2017, J. Comput. Mediat. Commun..

[4]  H. Sebastian Seung,et al.  Learning the parts of objects by non-negative matrix factorization , 1999, Nature.

[5]  M. Hubert,et al.  A Robust Measure of Skewness , 2004 .

[6]  John W. Emerson,et al.  Nonparametric Goodness-of-Fit Tests for Discrete Null Distributions , 2011, R J..

[7]  Michael I. Jordan,et al.  Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..

[8]  Kai Sun.  Explanation of Log-Normal Distributions and Power-Law Distributions in Biology and Social Science , 2004 .

[9]  Anders Henten,et al.  Business Models in Social Networking , 2009 .

[10]  M. McCombs.  Agenda setting function of mass media , 1977 .

[11]  Sanjay Krishnan,et al.  A methodology for learning, analyzing, and mitigating social influence bias in recommender systems , 2014, RecSys '14.

[12]  Virgílio A. F. Almeida,et al.  Characterizing user behavior in online social networks , 2009, IMC '09.

[13]  Simon Hegelich,et al.  The Communication Behavior of German MPs on Twitter: Preaching to the Converted and Attacking Opponents , 2015 .

[14]  Qiang Yang,et al.  One-Class Collaborative Filtering , 2008, 2008 Eighth IEEE International Conference on Data Mining.

[15]  Zhi-Hua Zhou,et al.  Ieee Transactions on Knowledge and Data Engineering 1 Training Cost-sensitive Neural Networks with Methods Addressing the Class Imbalance Problem , 2022 .

[16]  D. Ruths,et al.  Social media for large studies of behavior , 2014, Science.

[17]  Martin Hilbert,et al.  One Step, Two Step, Network Step? Complementary Perspectives on Communication Flows in Twittered Citizen Protests , 2017 .

[18]  M. Hubert,et al.  Outlier detection for skewed data , 2008 .

[19]  Joel Nothman,et al.  Learning multilingual named entity recognition from Wikipedia , 2013, Artif. Intell..

[20]  Mark Johnson,et al.  More Efficient Topic Modelling Through a Noun Only Approach , 2015, ALTA.

[21]  Wolfgang Lezius,et al.  TIGER: Linguistic Interpretation of a German Corpus , 2004 .

[22]  Mariarosaria Taddeo,et al.  The ethics of algorithms: Mapping the debate , 2016, Big Data Soc..

[23]  Chang-Tien Lu,et al.  Outlier Detection , 2008, Encyclopedia of GIS.

[24]  Orestis Papakyriakopoulos,et al.  Social media and microtargeting: Political data processing and the consequences for Germany , 2018, Big Data & Society.

[25]  Matthew K. O. Lee,et al.  The Continuance of Online Social Networks: How to Keep People Using Facebook? , 2010, 2010 43rd Hawaii International Conference on System Sciences.

[26]  Samy Bengio,et al.  Adversarial examples in the physical world , 2016, ICLR.

[27]  Mark Johnson,et al.  An Improved Non-monotonic Transition System for Dependency Parsing , 2015, EMNLP.

[28]  Seetha Hari,et al.  Learning From Imbalanced Data , 2019, Advances in Computer and Electrical Engineering.

[29]  C. Mouffe.  The Democratic Paradox , 2000 .

[30]  Piet Van Mieghem,et al.  Are human interactivity times lognormal? , 2016, ArXiv.

[31]  Taina Bucher,et al.  Want to be on the top? Algorithmic power and the threat of invisibility on Facebook , 2012, New Media Soc..

[32]  Filippo Menczer,et al.  Online Human-Bot Interactions: Detection, Estimation, and Characterization , 2017, ICWSM.

[33]  M. Stephens,et al.  K-Sample Anderson–Darling Tests , 1987 .

[34]  XuanLong Nguyen,et al.  Conic Scan-and-Cover algorithms for nonparametric topic modeling , 2017, NIPS.

[35]  Christian Doerr,et al.  Lognormal distribution in the digg online social network , 2011 .

[36]  Patrick D. McDaniel,et al.  On the (Statistical) Detection of Adversarial Examples , 2017, ArXiv.

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

[38]  Mia Hubert,et al.  An adjusted boxplot for skewed distributions , 2008, Comput. Stat. Data Anal..

[39]  John Riedl,et al.  Is seeing believing?: how recommender system interfaces affect users' opinions , 2003, CHI '03.

[40]  Orestis Papakyriakopoulos,et al.  Effects of Social Bots in the Iran-Debate on Twitter , 2018, ArXiv.

[41]  Lada A. Adamic,et al.  Exposure to ideologically diverse news and opinion on Facebook , 2015, Science.

[42]  Jens Grossklags,et al.  A Democracy Called Facebook? Participation as a Privacy Strategy on Social Media , 2018, APF.

[43]  Jenna Burrell,et al.  How the machine ‘thinks’: Understanding opacity in machine learning algorithms , 2016 .

[44]  Sujin Choi,et al.  The Two-Step Flow of Communication in Twitter-Based Public Forums , 2015 .

[45]  Kristina Lerman,et al.  Information Contagion: An Empirical Study of the Spread of News on Digg and Twitter Social Networks , 2010, ICWSM.

[46]  David Lazer,et al.  More Voices Than Ever? Quantifying Media Bias in Networks , 2011, ICWSM.

[47]  G. Enli,et al.  PERSONALIZED CAMPAIGNS IN PARTY-CENTRED POLITICS , 2013 .

[48]  Giovanni Luca Ciampaglia,et al.  The spread of low-credibility content by social bots , 2017, Nature Communications.

[49]  Karrie Karahalios,et al.  Auditing Algorithms : Research Methods for Detecting Discrimination on Internet Platforms , 2014 .

[50]  W. R. Buckland,et al.  Outliers in Statistical Data , 1979 .

[51]  Helen Nissenbaum,et al.  From Preemption to Circumvention: If Technology Regulates Why Do We Need Regulation (and Vice Versa)? , 2011 .

[52]  Andrew Schaap,et al.  Agonism in divided societies , 2006 .

[53]  Charles E. Heckler,et al.  Applied Multivariate Statistical Analysis , 2005, Technometrics.

[54]  Chein-I Chang,et al.  Robust radial basis function neural networks , 1999, IEEE Trans. Syst. Man Cybern. Part B.

[55]  Frank A. Pasquale.  The Black Box Society: The Secret Algorithms That Control Money and Information , 2015 .

[56]  Teresa Correa,et al.  Who interacts on the Web?: The intersection of users' personality and social media use , 2010, Comput. Hum. Behav..

[57]  Mitsugu Matsushita,et al.  Statistical properties of complex systems -lognormal and related distributions- , 2012 .

[58]  Brian E. Weeks,et al.  Online Influence? Social Media Use, Opinion Leadership, and Political Persuasion , 2015 .