Polarization on Social Media

Loading...
Thumbnail Image
Journal Title
Journal ISSN
Volume Title
School of Science | Doctoral thesis (article-based) | Defence date: 2018-02-07
Date
2018
Major/Subject
Mcode
Degree programme
Language
en
Pages
67 + app. 127
Series
Aalto University publication series DOCTORAL DISSERTATIONS, 20/2018
Abstract
Social media and the web have provided a foundation where users can easily access diverse information from around the world. However, over the years, various factors, such as user homophily (social network structure), and algorithmic filtering (e.g., news feeds and recommendations) have narrowed the breadth of content that a user consumes. This has lead to an ever-increasing cycle where users on social media only consume content that agrees with their beliefs and hence are recommended more such content, ultimately leading to a polarized society where diverse opinions are not encouraged. This thesis provides a broad overview of polarization on social media, along with algorithmic techniques to identify polarized topics, understanding their properties over time, and finally, to reduce polarization. First, we provide methods to identify polarized topics automatically from social-media streams. Our methods are mainly based on interaction networks, i.e., networks of social media users, connected through certain types of interactions. We first show that polarized topics have a special bi-clustered structure in their retweet network and propose an algorithm to quantify the degree of polarization by using a random walk on this network. We then make use of sub-graph patterns (motifs) in the reply network of users to show that we can easily identify polarized topics using such patterns. Since our analysis does not use content, our methods are able to generalize to any topic, domain and language. Next, we study the dynamic aspects of the process of polarization. We understand what happens to the interaction networks defined above in case of a sudden increase in interest of users on the topic. We then address the question on whether polarization on Twitter has increased over the last 8 years and find evidence to support that it does. Finally, given these findings, we design algorithms to reduce polarization. We propose two approaches. In the first approach, we propose connecting users with opposing viewpoints in order to reduce polarization. Our method takes into account the users' interests and their current level of polarization to help them get connected to the people they feel comfortable in doing so. In the second approach, we take an information-diffusion route. We pose the problem of reducing polarization as a task of spreading information that reaches both sides of the polarized topic.
Description
Supervising professor
Gionis, Aristides, Prof., Aalto University, Department of Computer Science, Finland
Keywords
polarization, graph mining, social media, filter bubble, echo chambers
Other note
Parts
  • [Publication 1]: Kiran Garimella, Gianmarco De Francisci Morales, Aristides Gionis, Michael Mathioudakis. Exploring Controversy in Twitter. Proceedings of the 19th ACM Conference on Computer Supported Cooperative Work and Social Computing Companion, 33–36, February 2016.
    DOI: 10.1145/2818052.2874318 View at publisher
  • [Publication 2]: Kiran Garimella, Gianmarco De Francisci Morales, Aristides Gionis, Michael Mathioudakis. Reducing Controversy by Connecting Opposing Views. Proceedings of the 10th ACM International Conference on Web Search and Data Mining, 81–90, February 2017.
    DOI: 10.1145/3018661.3018703 View at publisher
  • [Publication 3]: Kiran Garimella, Gianmarco De Francisci Morales, Aristides Gionis, Michael Mathioudakis. Exposing Twitter Users to Contrarian News. Proceedings of the 26th International World Wide Web Conference Companion, 201–205, April 2017.
    DOI: 10.1145/3041021.3054737 View at publisher
  • [Publication 4]: Kiran Garimella, Ingmar Weber. A Long-Term Analysis of Polarization on Twitter. Proceedings of the 11th AAAI International Conference on Web and Social Media, 53–57, May 2017.
  • [Publication 5]: Kiran Garimella, Gianmarco De Francisci Morales, Aristides Gionis, Michael Mathioudakis. The Effect of Collective Attention on Controversial Debates on Social Media. Proceedings of the 10th Annual ACM Web Science Conference, 43–52, July 2017.
    DOI: 10.1145/3091478.3091486 View at publisher
  • [Publication 6]: Kiran Garimella, Gianmarco De Francisci Morales, Aristides Gionis, Michael Mathioudakis. Factors in Recommending Contrarian Content on Social Media. Proceedings of the 10th Annual ACM Web Science Conference, 263–266, July VII Mauro Coletto, Kiran Garimella, Claudio Luchesse, Aristides Gionis. Automatic Controversy Detection in Social Media: a Content-independent Motifbased Approach. Online Social Networks and Media Journal, 22–31, October 2017.
    DOI: 10.1145/3091478.3091515 View at publisher
  • [Publication 7]: Mauro Coletto, Kiran Garimella, Claudio Luchesse, Aristides Gionis. Automatic Controversy Detection in Social Media: a Content-independent Motifbased Approach. Online Social Networks and Media Journal, 22–31, October2017.
    DOI: 10.1016/j.osnem.2017.10.001 View at publisher
  • [Publication 8]: Kiran Garimella, Gianmarco De Francisci Morales, Aristides Gionis, Michael Mathioudakis. Quantifying Controversy on Social Media. Transactions on Social Computing 2017, Accepted for publication, July 2017.
  • [Publication 9]: Kiran Garimella, Aristides Gionis, Nikos Parotsidis, Nikolaj Tatti. Balancing Information Exposure on Social Networks. Proceedings of the 31st Annual Conference on Neural Information Processing Systems, 4666–4674, September 2017.
  • [Publication 10]: Kiran Garimella, Gianmarco De Francisci Morales, Aristides Gionis, Michael Mathioudakis. Political Discourse on Social Media: Echo Chambers, Gatekeepers, and the Price of Bipartisanship. Accepted for publication at the 2018World Wide Web Conference, Jan 2018.
Citation