A Network Topology Approach to Bot Classification

TL;DR

This paper explores using social network topology features to classify Twitter users as bots or humans, achieving a 70% accuracy with an unsupervised learning method.

Contribution

It introduces a novel approach that relies solely on network topology to detect social bots, demonstrating its effectiveness with empirical results.

Findings

Achieved 70% detection accuracy using network topology features.

Unsupervised machine learning can effectively distinguish bots from humans.

Network topology alone can be a valuable indicator for bot detection.

Abstract

Automated social agents, or bots, are increasingly becoming a problem on social media platforms. There is a growing body of literature and multiple tools to aid in the detection of such agents on online social networking platforms. We propose that the social network topology of a user would be sufficient to determine whether the user is a automated agent or a human. To test this, we use a publicly available dataset containing users on Twitter labelled as either automated social agent or human. Using an unsupervised machine learning approach, we obtain a detection accuracy rate of 70%.