CRUSH: Contextually Regularized and User anchored Self-supervised Hate speech Detection

TL;DR

CRUSH is a novel hate speech detection framework that leverages user-anchored self-supervision and contextual regularization, achieving significant improvements over previous methods on social media datasets.

Contribution

It introduces a new framework combining user-anchored self-supervision with contextual regularization for improved hate speech detection.

Findings

Achieves 1-12% performance improvement over previous methods.

Effective across multiple datasets and task types.

Enhances hate speech detection accuracy in social media contexts.

Abstract

The last decade has witnessed a surge in the interaction of people through social networking platforms. While there are several positive aspects of these social platforms, the proliferation has led them to become the breeding ground for cyber-bullying and hate speech. Recent advances in NLP have often been used to mitigate the spread of such hateful content. Since the task of hate speech detection is usually applicable in the context of social networks, we introduce CRUSH, a framework for hate speech detection using user-anchored self-supervision and contextual regularization. Our proposed approach secures ~ 1-12% improvement in test set metrics over best performing previous approaches on two types of tasks and multiple popular english social media datasets.