Assessing Gender Bias in Predictive Algorithms using eXplainable AI

2022/03/19 by Cristina Manresa-Yee, Manresa-Yee, Cristina, Silvia Ramis +1
Computer Science · Medicine · Psychology · #Artificial Intelligence in Healthcare and Education #Artificial intelligence #Computer science #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Gender bias #Human-Computer Interaction (cs.HC) #Implicit bias #Machine Learning (cs.LG) #Machine learning #Psychology #Race (biology) #Racial bias #Social psychology #Sociology #cs.HC #cs.LG

paper · pdf · doi:10.48550/arxiv.2203.10264

published in arXiv (Cornell University) (Cornell University)

arxiv created 2022/03/19 · openalex publication_date 2022/03/19 · arxiv updated 2022/03/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/08

Abstract

Predictive algorithms have a powerful potential to offer benefits in areas as varied as medicine or education. However, these algorithms and the data they use are built by humans, consequently, they can inherit the bias and prejudices present in humans. The outcomes can systematically repeat errors that create unfair results, which can even lead to situations of discrimination (e.g. gender, social or racial). In order to illustrate how important is to count with a diverse training dataset to avoid bias, we manipulate a well-known facial expression recognition dataset to explore gender bias and discuss its implications.

Related

• Responsible AI: Gender bias assessment in emotion recognition
• Biased Heritage: How Datasets Shape Models in Facial Expression Recognition
• Fairness in AI Systems: Mitigating gender bias from language-vision models
• Gender Slopes: Counterfactual Fairness for Computer Vision Models by Attribute Manipulation
• End-To-End Bias Mitigation: Removing Gender Bias in Deep Learning