Towards Responsible AI: A Design Space Exploration of Human-Centered Artificial Intelligence User Interfaces to Investigate Fairness

Abstract

With Artificial intelligence (AI) to aid or automate decision-making advancing rapidly, a particular concern is its fairness. In order to create reliable, safe and trustworthy systems through human-centred artificial intelligence (HCAI) design, recent efforts have produced user interfaces (UIs) for AI experts to investigate the fairness of AI models. In this work, we provide a design space exploration that supports not only data scientists but also domain experts to investigate AI fairness. Using loan applications as an example, we held a series of workshops with loan officers and data scientists to elicit their requirements. We instantiated these requirements into FairHIL, a UI to support human-in-the-loop fairness investigations, and describe how this UI could be generalized to other use cases. We evaluated FairHIL through a think-aloud user study. Our work contributes better designs to investigate an AI model’s fairness—and move closer towards responsible AI.

Acknowledgement

Work by City, University of London was supported by Fujitsu Limited under a research contract.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Notes on contributors

Yuri Nakao

Yuri Nakao is a Researcher at the Research Center for AI Ethics, Fujitsu Limited, and a Ph.D. student at the Graduate School of Arts and Sciences, University of Tokyo. His research focus is on human autonomy in responsible technology, combining perspectives of Human-Computer Interaction, and Science, Technology and Society (STS).

Lorenzo Strappelli

Lorenzo Strappelli is a User Experience Designer with a Master of Science in Human-Computer Interaction Design, which he completed at City, University of London. He currently works at the BBC on projects exploring ethical design and has an interest in AI fairness and the challenges of emerging technology.

Simone Stumpf

Simone Stumpf is a Reader in Responsible and Interactive AI at University of Glasgow, UK, with a research focus on user interactions with AI systems. Her work in Explanatory Debugging for interactive machine learning has provided design principles for enabling better Human-Computer Interaction and AI transparency.

Aisha Naseer

Aisha Naseer is a Research Manager at Fujitsu Research of Europe Limited UK, leading AI Ethics activities. She is a founding Editorial Board member of the Springer Journal of AI and Ethics. She received a global recognition of being selected as the “100 Brilliant Women in AI Ethics List 2022.”

Daniele Regoli

Daniele Regoli is a senior Data Scientist at Intesa Sanpaolo. He has a background in theoretical physics, with a Ph.D. in cosmology from the University of Bologna and a Master in mathematical finance. He worked for several years as researcher on mathematical models applied to finance and economics.

Giulia Del Gamba

Giulia Del Gamba, a law graduate, works at Intesa Sanpaolo as an AI ethicist and legal advisor. In 2017, she worked at the European Data Protection Supervisor. Currently she sits on the Founding Editorial Board for Springer’s AI & Ethics Journal and she deals with European Digital Policies.