Unfairness towards subjective opinions in Machine Learning

TL;DR

This paper introduces a new form of unfairness in Machine Learning, termed exclusion of opinions, and proposes methods to quantify, visualize, and mitigate this bias to improve real-world applications.

Contribution

It formalizes the concept of unfairness as exclusion of opinions and offers quantification and visualization techniques to understand and address this issue.

Findings

Unfairness can be formalized as exclusion of opinions.

Visualization aids in understanding causes of unfairness.

Proposed methods can help mitigate opinion-based unfairness.

Abstract

Despite the high interest for Machine Learning (ML) in academia and industry, many issues related to the application of ML to real-life problems are yet to be addressed. Here we put forward one limitation which arises from a lack of adaptation of ML models and datasets to specific applications. We formalise a new notion of unfairness as exclusion of opinions. We propose ways to quantify this unfairness, and aid understanding its causes through visualisation. These insights into the functioning of ML-based systems hint at methods to mitigate unfairness.