Suum Cuique: Studying Bias in Taboo Detection with a Community Perspective

TL;DR

This paper introduces a community-based approach to studying bias in taboo language detection, revealing significant biases against African Americans and South Asians, and showing that community-aligned judgments can reduce false positives.

Contribution

It presents a novel community-specific classification method to analyze bias in taboo detection, addressing limitations of previous community-agnostic approaches.

Findings

Biases are largest against African Americans in most datasets

Strong biases are also found against South Asians

Community-aligned judgments can reduce false positive taboo classifications

Abstract

Prior research has discussed and illustrated the need to consider linguistic norms at the community level when studying taboo (hateful/offensive/toxic etc.) language. However, a methodology for doing so, that is firmly founded on community language norms is still largely absent. This can lead both to biases in taboo text classification and limitations in our understanding of the causes of bias. We propose a method to study bias in taboo classification and annotation where a community perspective is front and center. This is accomplished by using special classifiers tuned for each community's language. In essence, these classifiers represent community level language norms. We use these to study bias and find, for example, biases are largest against African Americans (7/10 datasets and all 3 classifiers examined). In contrast to previous papers we also study other communities and find, for example, strong biases against South Asians. In a small scale user study we illustrate our key idea which is that common utterances, i.e., those with high alignment scores with a community (community classifier confidence scores) are unlikely to be regarded taboo. Annotators who are community members contradict taboo classification decisions and annotations in a majority of instances. This paper is a significant step toward reducing false positive taboo decisions that over time harm minority communities.