Lifelong Learning of Hate Speech Classification on Social Media

TL;DR

This paper introduces a lifelong learning approach for hate speech classification on social media, combining variational representation learning with a memory module to adapt to evolving data without forgetting previous knowledge.

Contribution

It proposes a novel method integrating VRL and LB-SOINN to improve continual learning in hate speech detection tasks.

Findings

Outperforms existing lifelong learning techniques

Reduces catastrophic forgetting in hate speech classification

Enhances adaptability to new social media data

Abstract

Existing work on automated hate speech classification assumes that the dataset is fixed and the classes are pre-defined. However, the amount of data in social media increases every day, and the hot topics changes rapidly, requiring the classifiers to be able to continuously adapt to new data without forgetting the previously learned knowledge. This ability, referred to as lifelong learning, is crucial for the real-word application of hate speech classifiers in social media. In this work, we propose lifelong learning of hate speech classification on social media. To alleviate catastrophic forgetting, we propose to use Variational Representation Learning (VRL) along with a memory module based on LB-SOINN (Load-Balancing Self-Organizing Incremental Neural Network). Experimentally, we show that combining variational representation learning and the LB-SOINN memory module achieves better performance than the commonly-used lifelong learning techniques.