Overview

This book informs readers on how to understand, detect, and mitigate hate speech in online social media. The authors first cover the definition of hate speech and how its prevalence can be measured on online social media platforms using text and graph-based methods.

Detection and Models

The book then describes the process of detecting hate speech and presents a comprehensive account of the AI models that are currently being used. Further, the authors discuss the associated challenges that must be overcome while using these models.

Mitigation Techniques

The book concludes with an overview of the mitigation techniques for hate speech, including blocking or suspension of the accounts (hard technique) and counterspeech (soft technique), and a discussion of the effects of these techniques on social media platforms.