Mean Birds: Detecting Aggression and Bullying on Twitter

TL;DR

This paper introduces a scalable machine learning approach to detect bullying and aggression on Twitter by analyzing user behavior, text, and network features, achieving over 90% accuracy in identifying such users.

Contribution

It presents a novel, comprehensive methodology combining multiple attributes to effectively identify cyberbullies and aggressors on social media.

Findings

Bullies post less and are less popular than regular users.

Aggressors tend to be more popular and post more negativity.

The approach achieves over 90% AUC in detection accuracy.

Abstract

In recent years, bullying and aggression against users on social media have grown significantly, causing serious consequences to victims of all demographics. In particular, cyberbullying affects more than half of young social media users worldwide, and has also led to teenage suicides, prompted by prolonged and/or coordinated digital harassment. Nonetheless, tools and technologies for understanding and mitigating it are scarce and mostly ineffective. In this paper, we present a principled and scalable approach to detect bullying and aggressive behavior on Twitter. We propose a robust methodology for extracting text, user, and network-based attributes, studying the properties of cyberbullies and aggressors, and what features distinguish them from regular users. We find that bully users post less, participate in fewer online communities, and are less popular than normal users, while aggressors are quite popular and tend to include more negativity in their posts. We evaluate our methodology using a corpus of 1.6M tweets posted over 3 months, and show that machine learning classification algorithms can accurately detect users exhibiting bullying and aggressive behavior, achieving over 90% AUC.