Classifier (UML)

Set (abstract data type)

Data mining

Computer science

Natural language processing

Suite

Political science

Data science

Artificial intelligence

Information retrieval

Programming language

Machine learning

Unintended consequences

Unintended bias in Machine Learning can manifest as systemic differences in performance for different demographic groups, potentially compounding existing challenges to fairness in society at large. In this paper, we introduce a suite of threshold-agnostic metrics that provide a nuanced view of this unintended bias, by considering the various ways that a classifier’s score distribution can vary across designated groups. We also introduce a large new test set of online comments with crowd-sourced annotations for identity references. We use this to show how our metrics can be used to find new and potentially subtle unintended bias in existing public models.

Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification