Examining Gender and Race Bias in Two Hundred Sentiment Analysis Systems
arXiv:1805.04508
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.
In Proceedings of the 7th Joint Conference on Lexical and Computational Semantics (*SEM), New Orleans, USA, 2018
References in corpus (3)
Cited by in corpus (11)
- Closing the AI Accountability Gap: Defining an End-to-End Framework for Internal Algorithmic Auditing
- Towards Equity and Algorithmic Fairness in Student Grade Prediction
- Bias in Machine Learning -- What is it Good for?
- Unmasking Contextual Stereotypes: Measuring and Mitigating BERT's Gender Bias
- What's in the Box? A Preliminary Analysis of Undesirable Content in the Common Crawl Corpus
- Artificial mental phenomena: Psychophysics as a framework to detect perception biases in AI models
- Unified Adversarial Invariance
- Modeling Techniques for Machine Learning Fairness: A Survey
- Towards Reducing Bias in Gender Classification
- AI and Holistic Review: Informing Human Reading in College Admissions
- Assessing gender bias in medical and scientific masked language models with StereoSet