• Corpus ID: 204797795

Estimating the Political Orientation of Twitter Users in Homophilic Networks

  title={Estimating the Political Orientation of Twitter Users in Homophilic Networks},
  author={Morteza Shahrezaye and Orestis Papakyriakopoulos and Juan Carlos Medina Serrano and Simon Hegelich},
  booktitle={AAAI Spring Symposium: Interpretable AI for Well-being},
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… 

Tables from this paper

Understanding big social networks: Applied methods for computational social science

This dissertation lies on generating political knowledge from the huge amounts of data being generated on online social media platforms, and a wide range of algorithms developed have the goal of filling the theoretical gap between the different aspects of social sciences and computational sciences.

Impact of politically biased data on hate speech classification

It is shown that political bias negatively impairs the performance of hate speech classifiers and an explainable machine learning model can help to visualize such bias within the training data.



Birds of the Same Feather Tweet Together: Bayesian Ideal Point Estimation Using Twitter Data

Politicians and citizens increasingly engage in political conversations on social media outlets such as Twitter. In this article, I show that the structure of the social networks in which they are

Quantifying Political Leaning from Tweets and Retweets

By drawing a correspondence between tweeting and retweeting behavior, political leaning estimation is formulated as an ill-posed linear inverse problem and is a simple and scalable approach that does not require explicit knowledge of the network topology.

Computing political preference among twitter followers

A novel method for computing preference among an organization's Twitter followers is presented and an application of this technique is presented to estimate political preference of the audiences of U.S. media outlets.

Predicting Swedish elections with Twitter: A case for stochastic link structure analysis

Evidence is presented of how a well-known link prediction algorithm, can reveal an authoritative structural link formation within which the popularity of the political accounts along with their neighbourhoods, shows strong correlation with the standing of electoral outcomes.

Limits of Electoral Predictions Using Twitter

This work applies techniques that had reportedly led to positive election predictions in the past, on the Twitter data collected from the 2010 US congressional elections, but finds no correlation between the analysis results and the electoral outcomes, contradicting previous reports.

Social media and microtargeting: Political data processing and the consequences for Germany

This paper explores the possibility to identify micro groups of users, which can potentially be targeted with special campaign messages, and how this approach can be expanded to large parts of the electorate, and discusses the ethical and political implications for the German political system.

Virtual Community Attraction: Why People Hang Out Online

It is suggested that virtual community managers should emphasize not only the content but also encourage the friendship and social support aspects as well if they wish to increase the success of their virtual community.

Large networks of rational agents form persistent echo chambers

It is shown that ECs can theoretically emerge amongst error-free Bayesian agents, and that larger networks encourage rather than ameliorate EC growth, suggesting that the network structure itself contributes to echo chamber formation.

The triple‐filter bubble: Using agent‐based modelling to test a meta‐theoretical framework for the emergence of filter bubbles and echo chambers

Simulations show that, even without any social or technological filters, echo chambers emerge as a consequence of cognitive mechanisms, such as confirmation bias, under conditions of central information propagation through channels reaching a large part of the population.

Social Identity Theory and Self‐categorization Theory: A Historical Review

The social identity approach (comprising social identity theory and self-categorization theory) is a highly influential theory of group processes and intergroup relations, having redefined how we