Hate Speech Detection via Dual Contrastive Learning

The fast spread of hate speech on social media impacts the Internet environment and our society by increasing prejudice and hurting people. Detecting hate speech has aroused broad attention in the field of natural language processing. Although hate speech detection has been addressed in recent work, this task still faces two inherent unsolved challenges. The first challenge lies in the complex semantic information conveyed in hate speech, particularly the interference of insulting words in hate speech detection. The second challenge is the imbalanced distribution of hate speech and non-hate speech, which may significantly deteriorate the performance of models. To tackle these challenges, we propose a novel dual contrastive learning (DCL) framework for hate speech detection. Our framework jointly optimizes the self-supervised and the supervised contrastive learning loss for capturing span-level information beyond the token-level emotional semantics used in existing models, particularly detecting speech containing abusive and insulting words. Moreover, we integrate the focal loss into the dual contrastive learning framework to alleviate the problem of data imbalance. We conduct experiments on two publicly available English datasets, and experimental results show that the proposed model outperforms the state-of-the-art models and precisely detects hate speeches.

I. Introduction

The widespread use of social media provides people with a broader space for communication and information exchange. People can freely express themselves on social media. While accelerating the dissemination of public opinions, social media also leads to the dissemination of undesirable speech, such as online hate speech. Nockleyby [1] described hate speech as any kind of communication in speech, writing, or behavior, that attacks or uses pejorative or discriminatory language concerning a person or a group based on their religion, nationality, race, gender, or other identity factors.