Hierarchical CVAE for Fine-Grained Hate Speech Classification

Abstract

Existing work on automated hate speech detection typically focuses on binary classification or on differentiating among a small set of categories. In this paper, we propose a novel method on a fine-grained hate speech classification task, which focuses on differentiating among 40 hate groups of 13 different hate group categories. We first explore the Conditional Variational Autoencoder (CVAE) as a discriminative model and then extend it to a hierarchical architecture to utilize the additional hate category information for more accurate prediction. Experimentally, we show that incorporating the hate category information for training can significantly improve the classification performance and our proposed model outperforms commonly-used discriminative models.

References in corpus (8)

• Stochastic Backpropagation and Approximate Inference in Deep Generative Models
• A C-LSTM Neural Network for Text Classification
• Markov Chain Monte Carlo and Variational Inference: Bridging the Gap
• Automated Hate Speech Detection and the Problem of Offensive Language
• Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders
• Generative and Discriminative Text Classification with Recurrent Neural Networks
• Variational Neural Machine Translation
• Recognizing Explicit and Implicit Hate Speech Using a Weakly Supervised Two-path Bootstrapping Approach