BriefGPT.xyz
May, 2020
仇恨言论和辱骂语料库中的交叉偏见
Intersectional Bias in Hate Speech and Abusive Language Datasets
HTML
PDF
Jae Yeon Kim, Carlos Ortiz, Sarah Nam, Sarah Santiago, Vivek Datta
TL;DR
本研究通过对 Twitter 数据集进行分类，发现算法对于辱骂言论和仇恨言论的判别对非裔美国人和非裔男性的偏见较强，这提供了有关算法数据集中交叉偏见的首个系统性证据。
Abstract
algorithms
are widely applied to detect
hate speech
and abusive language in
social media
. We investigated whether the human-annotated data
→