Examining Gender and Race Bias in Two Hundred Sentiment Analysis Systems
Svetlana Kiritchenko Saif M. Mohammad National Research Council Canada
Abstract
Automatic machine learning systems can inadvertently accentuate and perpetuate inappropriate human biases. Past work on examining inappropriate biases has largely focused on just individual systems. Further, there is no benchmark dataset for examining inappropriate biases in systems. Here for the first time, we present the Equity Evaluation Corpus (EEC), which consists of 8,640 English sentences carefully chosen to tease out biases towards certain races and genders. We use the dataset to examine 219 automatic sentiment analysis systems that took part in a recent shared task, SemEval-2018 Task 1 ‘Affect in Tweets’. We find that several of the systems show statistically significant bias; that is, they consistently provide slightly higher sentiment intensity predictions for one race or one gender. We make the EEC freely available.
中文速览
情感分析（sentiment analysis）系统正在被越来越广泛地应用于现实决策，但这些系统是否会因为句子中提到的人物性别或种族不同而给出不同的情感强度评分？为了系统性地回答这个问题，研究者构建了一个名为"公平评估语料库"（Equity Evaluation Corpus, EEC）的基准数据集，包含8640个精心设计的英文句子，这些句子成对出现，除了人名或人称代词（代表不同种族或性别）之外完全一致。借助这个数据集，研究者对参加SemEval-2018情感分析竞赛的219个系统进行了偏见检测，结果发现其中大多数系统存在统计显著的偏见——即对涉及特定性别或种族的句子会系统性地给出略高或略低的情感强度预测。这项工作是首个针对大规模情感分析系统偏见的基准测评，EEC数据集的公开发布为后续研究者检验和改进NLP系统的公平性提供了可复用的工具。
原文 arXiv:1805.04508;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1805.04508v1