Enriching Abusive Language Detection with Community Context

TL;DR

This paper shows that incorporating community context into abusive language detection models improves their accuracy and reduces false positives, helping to better distinguish between harmful and benign uses of language.

Contribution

It introduces the idea that community context, including community support patterns, enhances abusive language classification beyond user and thread features.

Findings

Community clusters form based on support towards abuse victims.

Community context improves classifier accuracy.

Community context reduces false positive rates.

Abstract

Uses of pejorative expressions can be benign or actively empowering. When models for abuse detection misclassify these expressions as derogatory, they inadvertently censor productive conversations held by marginalized groups. One way to engage with non-dominant perspectives is to add context around conversations. Previous research has leveraged user- and thread-level features, but it often neglects the spaces within which productive conversations take place. Our paper highlights how community context can improve classification outcomes in abusive language detection. We make two main contributions to this end. First, we demonstrate that online communities cluster by the nature of their support towards victims of abuse. Second, we establish how community context improves accuracy and reduces the false positive rates of state-of-the-art abusive language classifiers. These findings suggest a promising direction for context-aware models in abusive language research.