Predictive Embeddings for Hate Speech Detection on Twitter
This addresses the problem of identifying hate speech, including racist and sexist content, on social media platforms, with an incremental improvement in efficiency.
The authors tackled hate speech detection on Twitter by developing a neural network approach using pre-trained word embeddings with pooling, achieving state-of-the-art F1 performance on three datasets while using fewer parameters and minimal preprocessing.
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.