Fairness and Decision-making in Collaborative Shift Scheduling Systems

Abstract

The strains associated with shift work decrease healthcare workers' well-being. However, shift schedules adapted to their individual needs can partially mitigate these problems. From a computing perspective, shift scheduling was so far mainly treated as an optimization problem with little attention given to the preferences, thoughts, and feelings of the healthcare workers involved. In the present study, we explore fairness as a central, human-oriented attribute of shift schedules as well as the scheduling process. Three in-depth qualitative interviews and a validating vignette study revealed that while on an abstract level healthcare workers agree on equality as the guiding norm for a fair schedule, specific scheduling conflicts should foremost be resolved by negotiating the importance of individual needs. We discuss elements of organizational fairness, including transparency and team spirit. Finally, we present a sketch for fair scheduling systems, summarizing key findings for designers in a readily usable way.

10 pages, 3 figures, to be published at CHI'20

References in corpus (2)

• Fairness in Machine Learning: Lessons from Political Philosophy
• Explaining Models: An Empirical Study of How Explanations Impact Fairness Judgment

Cited by in corpus (5)

• "There Is Not Enough Information": On the Effects of Explanations on Perceptions of Informational Fairness and Trustworthiness in Automated Decision-Making
• "Look! It's a Computer Program! It's an Algorithm! It's AI!": Does Terminology Affect Human Perceptions and Evaluations of Algorithmic Decision-Making Systems?
• Design and Appropriation of Computer-supported Self-scheduling Practices in Healthcare Shift Work
• Regulating Algorithmic Management: A Multi-Stakeholder Study of Challenges in Aligning Software and the Law for Workplace Scheduling
• Workload Balancing Among Heathcare Workers Under Uncertain Service Time Using Distributionally Robust Optimization