Improving echo chamber detection in social networks with new math tools
Revisiting the Objective of Echo Chamber Detection
Machine Learning
Summary
Detecting echo chambers means finding groups in social networks where members mostly agree on a topic but disagree with others. The paper’s authors show that this problem is unique and different from other network tasks like community detection. They introduce a new way to measure and find these echo chambers using advanced math called Fourier transforms of set functions. Their new algorithm performs better than existing methods on both fake and real-world data, uncovering groups that match known echo chambers more accurately.
What this means in practice
- •For social media platform teams: Identify groups of users showing strong agreement on topics but disagreement with others to better understand content polarization and moderation needs.
- •For online community managers: Detect tightly-knit groups within forums or networks that might be propagating homogeneous opinions for targeted community engagement or intervention.
Authors
Abylaikhan Bexeit, Kushani Perera, Shanika Karunasekera, Jean Honorio
Abstract
In this paper, we study the detection of an echo chamber in a social network, i.e., the identification of a set of nodes that agree on a topic, while disagreeing with the rest of nodes. We argue that this problem is different from other social network analysis problems such as community detection, and from other graph problems such as maximum graph cut and maximum clique. To the best of our knowledge, we are the first to formalize the objective function of echo chamber detection, by using the theory of Fourier transforms of set functions (Stobbe and Krause, 2012). We propose scalable semidefinite relaxation, solved via an interior point method and sparse linear algebra. Experimentally, our algorithm recovers the ground truth echo chamber better than competing methods on small synthetic experiments. Our algorithm produces echo chambers with better network properties than competing methods on large real-world datasets. To independently validate our proposed objective function, we show that our algorithm finds echo chambers with more agreements with suspended users than competing methods on a small real-world dataset.