Assessing Gender Bias in Predictive Algorithms using eXplainable AI
This work addresses fairness issues in AI for applications like medicine and education, but it is incremental as it uses existing methods on manipulated data.
The study investigated gender bias in predictive algorithms by manipulating a facial expression recognition dataset to demonstrate the importance of diverse training data, showing that biased datasets can lead to unfair outcomes.
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.