Assessing Gender Bias in Predictive Algorithms using eXplainable AI

TL;DR

This paper investigates gender bias in predictive algorithms, emphasizing the importance of diverse training data, by manipulating a facial expression dataset to reveal biases and discuss their societal implications.

Contribution

It demonstrates how bias can be introduced into predictive models through data manipulation and highlights the need for diverse datasets to mitigate discrimination.

Findings

Manipulating facial expression data reveals gender bias in algorithms.

Bias can lead to unfair and discriminatory outcomes.

Diverse training data is crucial for fair predictive modeling.

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.