# Understanding Abuse: A Typology of Abusive Language Detection Subtasks

## TL;DR

This paper proposes a typology of abusive language detection subtasks, clarifying their relationships and guiding researchers in data annotation and feature development for more effective detection methods.

## Contribution

It introduces a novel typology that categorizes abusive language detection subtasks, enhancing understanding and methodological consistency in the field.

## Key findings

- Clarifies relationships between different abusive language detection subtasks
- Provides guidelines for data annotation and feature construction
- Facilitates more targeted and effective detection approaches

## Abstract

As the body of research on abusive language detection and analysis grows, there is a need for critical consideration of the relationships between different subtasks that have been grouped under this label. Based on work on hate speech, cyberbullying, and online abuse we propose a typology that captures central similarities and differences between subtasks and we discuss its implications for data annotation and feature construction. We emphasize the practical actions that can be taken by researchers to best approach their abusive language detection subtask of interest.