Attention-based method for categorizing different types of online harassment language

TL;DR

This paper introduces a multi-attention RNN-based method for detecting various types of online harassment in tweets, addressing data imbalance with back-translation, and compares different RNN approaches.

Contribution

It proposes a novel multi-attention mechanism for harassment detection and tackles data imbalance, advancing NLP techniques for social media content moderation.

Findings

Effective harassment classification in tweets.

Improved handling of imbalanced datasets.

Comparison of RNN-based approaches.

Abstract

In the era of social media and networking platforms, Twitter has been doomed for abuse and harassment toward users specifically women. Monitoring the contents including sexism and sexual harassment in traditional media is easier than monitoring on the online social media platforms like Twitter, because of the large amount of user generated content in these media. So, the research about the automated detection of content containing sexual or racist harassment is an important issue and could be the basis for removing that content or flagging it for human evaluation. Previous studies have been focused on collecting data about sexism and racism in very broad terms. However, there is no much study focusing on different types of online harassment attracting natural language processing techniques. In this work, we present an multi-attention based approach for the detection of different types of harassment in tweets. Our approach is based on the Recurrent Neural Networks and particularly we are using a deep, classification specific multi-attention mechanism. Moreover, we tackle the problem of imbalanced data, using a back-translation method. Finally, we present a comparison between different approaches based on the Recurrent Neural Networks.