Hater-O-Genius Aggression Classification using Capsule Networks

TL;DR

This paper presents an ensemble of Capsule Networks for classifying aggressive tweets into covert, overt, or non-aggressive, achieving improved performance over previous models in hate speech detection.

Contribution

It introduces a novel ensemble architecture combining Capsule Networks for effective aggression classification in social media texts.

Findings

Achieved 65.2% F1 score on Facebook test set.

Ensemble of Capsule Networks outperforms previous state-of-the-art.

Each subnetwork learns unique feature representations.

Abstract

Contending hate speech in social media is one of the most challenging social problems of our time. There are various types of anti-social behavior in social media. Foremost of them is aggressive behavior, which is causing many social issues such as affecting the social lives and mental health of social media users. In this paper, we propose an end-to-end ensemble-based architecture to automatically identify and classify aggressive tweets. Tweets are classified into three categories - Covertly Aggressive, Overtly Aggressive, and Non-Aggressive. The proposed architecture is an ensemble of smaller subnetworks that are able to characterize the feature embeddings effectively. We demonstrate qualitatively that each of the smaller subnetworks is able to learn unique features. Our best model is an ensemble of Capsule Networks and results in a 65.2% F1 score on the Facebook test set, which results in a performance gain of 0.95% over the TRAC-2018 winners. The code and the model weights are publicly available at https://github.com/parthpatwa/Hater-O-Genius-Aggression-Classification-using-Capsule-Networks.