Polarisation in online social networks

Detecting polarisation using cross-community social ties

Bachelor Thesis (2026)
Author(s)

C. Olaru (TU Delft - Electrical Engineering, Mathematics and Computer Science)

Contributor(s)

Anna L.D. Latour – Mentor (TU Delft - Electrical Engineering, Mathematics and Computer Science)

Megha Khosla – Graduation committee member (TU Delft - Electrical Engineering, Mathematics and Computer Science)

Faculty
Electrical Engineering, Mathematics and Computer Science
More Info
expand_more
Publication Year
2026
Language
English
Graduation Date
26-06-2026
Awarding Institution
Delft University of Technology
Project
CSE3000 Research Project
Programme
Computer Science and Engineering
Faculty
Electrical Engineering, Mathematics and Computer Science
Downloads counter
3
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

The last decade has seen an uptick in political polarisation on online social networks. This has led to increasing distrust and antagonism, sometimes resulting in conflict. As such, studying the emergence of political polarisation is increasingly important in
the current political landscape. The field of network science provides ways to model the underlying structure of social networks. This facilitates the measurement and prediction of polarisation. We propose a way of predicting the emergence of political polarisation by looking at the community structure of a network. Specifically, we examine the extent to which social ties between members of different communities influence how political polarisation takes form. We measure polarisation on
two levels: ideological and relational. We experiment on synthetic networks, generated using two different models. One of the models produces networks with homogeneous community structures. The other generates them according to power law distributions. Our findings show a negative correlation between the fraction of cross-community social ties and the level of polarisation in the network.

Files

License info not available