Social Media Bot Detection using Dropout-GAN

TL;DR

This paper introduces a novel GAN-based method for detecting social media bots, employing multiple discriminators to improve accuracy and using the generator for data augmentation and evasion analysis.

Contribution

It presents a new Dropout-GAN framework with multiple discriminators for enhanced bot detection and explores the generator's role in data augmentation and evasion tactics.

Findings

Outperforms state-of-the-art bot detection methods in accuracy

Uses multiple discriminators to prevent mode collapse

Demonstrates the generator's ability to evade detection

Abstract

Bot activity on social media platforms is a pervasive problem, undermining the credibility of online discourse and potentially leading to cybercrime. We propose an approach to bot detection using Generative Adversarial Networks (GAN). We discuss how we overcome the issue of mode collapse by utilizing multiple discriminators to train against one generator, while decoupling the discriminator to perform social media bot detection and utilizing the generator for data augmentation. In terms of classification accuracy, our approach outperforms the state-of-the-art techniques in this field. We also show how the generator in the GAN can be used to evade such a classification technique.