Bot-Match: Social Bot Detection with Recursive Nearest Neighbors Search

TL;DR

Bot-Match introduces a semi-supervised recursive nearest neighbors search method for social bot detection, enabling analysts to identify similar malicious accounts without retraining models, thus addressing the limitations of traditional supervised algorithms.

Contribution

This paper presents Bot-Match, a novel similarity-based detection approach using social media embeddings and recursive nearest neighbors search for rapid threat mapping.

Findings

Effective identification of similar bot accounts without retraining

Addresses limitations of supervised machine learning in evolving social threats

Provides a semi-supervised framework for social cybersecurity analysis

Abstract

Social bots have emerged over the last decade, initially creating a nuisance while more recently used to intimidate journalists, sway electoral events, and aggravate existing social fissures. This social threat has spawned a bot detection algorithms race in which detection algorithms evolve in an attempt to keep up with increasingly sophisticated bot accounts. This cat and mouse cycle has illuminated the limitations of supervised machine learning algorithms, where researchers attempt to use yesterday's data to predict tomorrow's bots. This gap means that researchers, journalists, and analysts daily identify malicious bot accounts that are undetected by state of the art supervised bot detection algorithms. These analysts often desire to find similar bot accounts without labeling/training a new model, where similarity can be defined by content, network position, or both. A similarity based algorithm could complement existing supervised and unsupervised methods and fill this gap. To this end, we present the Bot-Match methodology in which we evaluate social media embeddings that enable a semi-supervised recursive nearest neighbors search to map an emerging social cybersecurity threat given one or more seed accounts.