Detecting Influence Campaigns in Social Networks Using the Ising Model

TL;DR

This paper introduces a novel Ising model-based method for detecting coordinated influence campaigns by bots in social networks, outperforming existing approaches in accuracy and enabling simultaneous identification of multiple bots.

Contribution

The paper develops a new probabilistic model using the Ising framework and a maximum likelihood approach to detect multiple coordinated bots simultaneously in social networks.

Findings

The Ising model-based algorithm outperforms existing methods in bot detection accuracy.

Bots exhibit heterophily, interacting more with humans than with each other.

Detected bots show evidence of a coordinated agenda.

Abstract

We consider the problem of identifying coordinated influence campaigns conducted by automated agents or bots in a social network. We study several different Twitter datasets which contain such campaigns and find that the bots exhibit heterophily - they interact more with humans than with each other. We use this observation to develop a probability model for the network structure and bot labels based on the Ising model from statistical physics. We present a method to find the maximum likelihood assignment of bot labels by solving a minimum cut problem. Our algorithm allows for the simultaneous detection of multiple bots that are potentially engaging in a coordinated influence campaign, in contrast to other methods that identify bots one at a time. We find that our algorithm is able to more accurately find bots than existing methods when compared to a human labeled ground truth. We also look at the content posted by the bots we identify and find that they seem to have a coordinated agenda.