CoSyn: Detecting Implicit Hate Speech in Online Conversations Using a Context Synergized Hyperbolic Network

TL;DR

This paper introduces CoSyn, a novel neural network that effectively detects implicit hate speech in online conversations by leveraging user and conversational context in hyperbolic space, outperforming existing methods.

Contribution

CoSyn is the first model to explicitly incorporate user and conversational context in hyperbolic space for implicit hate speech detection, with a novel context interaction mechanism.

Findings

Outperforms all baselines on 6 hate speech datasets

Achieves 1.24% to 57.8% absolute improvement in detection accuracy

Effectively captures implicit hate speech through context-aware modeling

Abstract

The tremendous growth of social media users interacting in online conversations has led to significant growth in hate speech, affecting people from various demographics. Most of the prior works focus on detecting explicit hate speech, which is overt and leverages hateful phrases, with very little work focusing on detecting hate speech that is implicit or denotes hatred through indirect or coded language. In this paper, we present CoSyn, a context-synergized neural network that explicitly incorporates user- and conversational context for detecting implicit hate speech in online conversations. CoSyn introduces novel ways to encode these external contexts and employs a novel context interaction mechanism that clearly captures the interplay between them, making independent assessments of the amounts of information to be retrieved from these noisy contexts. Additionally, it carries out all these operations in the hyperbolic space to account for the scale-free dynamics of social media. We demonstrate the effectiveness of CoSyn on 6 hate speech datasets and show that CoSyn outperforms all our baselines in detecting implicit hate speech with absolute improvements in the range of 1.24% - 57.8%.