Integrating Psychometrics and Computing Perspectives on Bias and Fairness in Affective Computing: A case study of automated video interviews

We provide a psychometric-grounded exposition of bias and fairness as applied to a typical machine learning (ML) pipeline for affective computing (AC). We expand on an interpersonal communication framework to elucidate how to identify sources of bias that may arise in the process of inferring human emotions and other psychological constructs from observed behavior. The various methods and metrics for measuring fairness and bias are discussed, along with pertinent implications within the U.S. legal context. We illustrate how to measure some types of bias and fairness in a case study involving automatic personality and hireability inference from multimodal data collected in video interviews for mock job applications. We encourage AC researchers and practitioners to encapsulate bias and fairness in their research processes and products and to consider their role, agency, and responsibility in promoting equitable and just systems.

Automated summary

This article provides a psychometric-grounded exposition of bias and fairness in affective computing, discussing how to identify sources of bias and measuring fairness and bias methods. The case study illustrates how to measure bias and fairness in automatic personality and hireability inference, encouraging researchers and practitioners to consider equity and justice in their research processes and products.