Measuring and moderating opinion polarization in online social networks (Master thesis)

Ματάκος, Αντώνιος


The polarization of society over controversial social issues has been the subject of study in social sciences for decades [22, 33]. The widespread usage of online social networks and social media and the tendency of people to connect and interact with like-minded individuals has only intensified the phenomenon of polarization [4]. In this thesis, we consider the problem of measuring and reducing polarization of opinions in a social network. Using a standard opinion formation model [15], we define the polarization index, which, given a network and the opinions of the individuals in the network, it quantifies the polarization observed in the network. Our measure captures the tendency of opinions to concentrate in network communities, creating an echo-chamber. Given a numerical measure of polarization in the network, we consider the problem of reducing polarization by convincing individuals (e.g., through education, exposure to diverse viewpoints, or incentives) to adopt a more neutral stand towards controversial issues. We formally define the ModerateInternal and ModerateExpressed problems, and we prove that both our problems are NP-hard. By exploiting the linear-algebraic characteristics of the opinion formation model we design polynomial-time algorithms for both problems, and efficient heuristics. We conduct our experiments on real-world datasets, with data from twitter representing well-known controversies. We demonstrate the validity of our metric, by comparing against other metrics, and observing the obtained value in both polarized and non-polarized settings. We also showcase the efficiency and the effectiveness of our algorithms and heuristics in practice.
Institution and School/Department of submitter: Πανεπιστήμιο Ιωαννίνων. Σχολή Θετικών Επιστημών. Τμήμα Μηχανικών Η/Υ & Πληροφορικής
Subject classification: Social networks
Keywords: Πόλωση,Κοινωνικά δίκτυα,Μοντέλο σχηματισμού απόψεων,Polarization,Social network,Social media,Opinion formation model
URI: http://olympias.lib.uoi.gr/jspui/handle/123456789/28124
Appears in Collections:Διατριβές Μεταπτυχιακής Έρευνας (Masters)

Files in This Item:
File Description SizeFormat 
Μ.Ε. ΜΑΤΑΚΟΣ ΑΝΤΩΝΙΟΣ 2017.pdf563.05 kBAdobe PDFView/Open



 Please use this identifier to cite or link to this item:
http://olympias.lib.uoi.gr/jspui/handle/123456789/28124
  This item is a favorite for 0 people.

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.