Predictive Embeddings for Hate Speech Detection on Twitter

TL;DR

This paper introduces a neural network approach utilizing pre-trained embeddings and pooling techniques to detect hate speech on Twitter, achieving high accuracy with fewer parameters and less preprocessing.

Contribution

The study presents a novel neural network model that outperforms existing methods in hate speech detection using minimal features and computational resources.

Findings

Achieves state-of-the-art F1 scores on three datasets

Uses significantly fewer parameters than previous models

Requires minimal feature preprocessing

Abstract

We present a neural-network based approach to classifying online hate speech in general, as well as racist and sexist speech in particular. Using pre-trained word embeddings and max/mean pooling from simple, fully-connected transformations of these embeddings, we are able to predict the occurrence of hate speech on three commonly used publicly available datasets. Our models match or outperform state of the art F1 performance on all three datasets using significantly fewer parameters and minimal feature preprocessing compared to previous methods.