Detecting Hate Speech in Social Media

TL;DR

This paper explores supervised classification techniques to detect hate speech in social media, distinguishing it from profanity, and establishes lexical baselines with promising accuracy, highlighting key challenges and future directions.

Contribution

It introduces a lexical baseline approach using character and word n-grams for hate speech detection and analyzes the main challenges in differentiating hate speech from profanity.

Findings

78% accuracy in classifying hate speech, profanity, and neutral posts

Main challenge is distinguishing hate speech from general profanity

Provides directions for improving hate speech detection methods

Abstract

In this paper we examine methods to detect hate speech in social media, while distinguishing this from general profanity. We aim to establish lexical baselines for this task by applying supervised classification methods using a recently released dataset annotated for this purpose. As features, our system uses character n-grams, word n-grams and word skip-grams. We obtain results of 78% accuracy in identifying posts across three classes. Results demonstrate that the main challenge lies in discriminating profanity and hate speech from each other. A number of directions for future work are discussed.