Attending the Emotions to Detect Online Abusive Language

TL;DR

This paper introduces an emotion-aware attention mechanism within a deep neural network to improve the detection of abusive language in online social media, achieving state-of-the-art results.

Contribution

It presents a novel emotion-aware attention mechanism and a new dataset for abusive language detection, advancing the accuracy of identifying offensive content online.

Findings

Achieved new state-of-the-art results on offensive language detection

Demonstrated effectiveness of emotion-aware attention in identifying abusive language

Validated the model across multiple datasets

Abstract

In recent years, abusive behavior has become a serious issue in online social networks. In this paper, we present a new corpus from a semi-anonymous social media platform, which contains the instances of offensive and neutral classes. We introduce a single deep neural architecture that considers both local and sequential information from the text in order to detect abusive language. Along with this model, we introduce a new attention mechanism called emotion-aware attention. This mechanism utilizes the emotions behind the text to find the most important words within that text. We experiment with this model on our dataset and later present the analysis. Additionally, we evaluate our proposed method on different corpora and show new state-of-the-art results with respect to offensive language detection.