Defining and Detecting Toxicity on Social Media: Context and Knowledge are Key

TL;DR

This paper emphasizes the importance of context and explicit knowledge in defining and detecting online toxicity, proposing a multi-dimensional approach grounded in social and psychological theory.

Contribution

It introduces a novel method that integrates explicit knowledge with statistical learning to identify multiple toxicity dimensions in social media content.

Findings

Incorporates social and psychological theory into toxicity detection.

Proposes a multi-dimensional toxicity identification approach.

Highlights the role of explicit knowledge in resolving ambiguity.

Abstract

Online platforms have become an increasingly prominent means of communication. Despite the obvious benefits to the expanded distribution of content, the last decade has resulted in disturbing toxic communication, such as cyberbullying and harassment. Nevertheless, detecting online toxicity is challenging due to its multi-dimensional, context sensitive nature. As exposure to online toxicity can have serious social consequences, reliable models and algorithms are required for detecting and analyzing such communication across the vast and growing space of social media. In this paper, we draw on psychological and social theory to define toxicity. Then, we provide an approach that identifies multiple dimensions of toxicity and incorporates explicit knowledge in a statistical learning algorithm to resolve ambiguity across such dimensions.