Estimating the Political Orientation of Twitter Users in Homophilic Networks

There have been many efforts to estimate the political orientation of citizens and political actors. With the burst of online social media use in the last two decades, this topic has undergone major changes. Many researchers and political campaigns have attempted to measure and estimate the political orientation of online social media users. In this paper, we use a combination of metric learning algorithms and label propagation methods to estimate the political orientation of Twitter users. We argue that the metric learning algorithm dramatically increases the accuracy of our model by accentuating the effect of homophilic networks. Homophilic networks are user clusters formed due to cognitive motivational processes linked with cognitive biases. We apply our method to a sample of Twitter users in Germany’s six-party political sphere. Our method obtains a significant accuracy of 62% using only 40 observations of training data for each political party.

[1]  Scott D. Brown,et al.  Why is accurately labelling simple magnitudes so hard , 2015 .

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

[3]  M. Haselton,et al.  The Evolution of Cognitive Bias , 2015 .

[4]  Tim Groseclose,et al.  A Measure of Media Bias , 2005 .

[5]  Derek L. Hansen,et al.  Computing political preference among twitter followers , 2011, CHI.

[6]  Kilian Q. Weinberger,et al.  Distance Metric Learning for Large Margin Nearest Neighbor Classification , 2005, NIPS.

[7]  Joe Bob Hester.  Setting the Agenda: The Mass Media and Public Opinion , 2005 .

[8]  Jens Koed Madsen,et al.  Large networks of rational agents form persistent echo chambers , 2018, Scientific Reports.

[9]  Panagiotis Takis Metaxas,et al.  Limits of Electoral Predictions Using Twitter , 2011, ICWSM.

[10]  Richard Barrett,et al.  Templates for the Solution of Linear Systems: Building Blocks for Iterative Methods , 1994, Other Titles in Applied Mathematics.

[11]  M. Hornsey.  Social Identity Theory and Self‐categorization Theory: A Historical Review , 2008 .

[12]  Daniel Gillblad,et al.  Predicting Swedish elections with Twitter: A case for stochastic link structure analysis , 2015, 2015 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM).

[13]  A. Tversky,et al.  On the psychology of prediction , 1973 .

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

[15]  Mung Chiang,et al.  Quantifying Political Leaning from Tweets and Retweets , 2013, ICWSM.

[16]  David Gefen,et al.  Virtual Community Attraction: Why People Hang Out Online , 2006, J. Comput. Mediat. Commun..

[17]  Christoph W Korn,et al.  How unrealistic optimism is maintained in the face of reality , 2011, Nature Neuroscience.

[18]  Zoubin Ghahramani,et al.  Learning from labeled and unlabeled data with label propagation , 2002 .

[19]  Jan Lorenz,et al.  The triple‐filter bubble: Using agent‐based modelling to test a meta‐theoretical framework for the emergence of filter bubbles and echo chambers , 2018, The British journal of social psychology.

[20]  Vladas Griskevicius,et al.  Science Current Directions in Psychological Goal-driven Cognition and Functional Behavior : the Fundamental-motives Framework on Behalf Of: Association for Psychological Science Goal-driven Cognition and Functional Behavior: the Fundamental-motives Framework the Fundamental Motives Framework , 2022 .

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