Improving Fairness in Adaptive Social Exergames via Shapley Bandits

Robert C. Gray, Jennifer Villareale, Thomas Boyd Fox, Diane H. Dallal, Santiago Ontanon, Danielle Arigo, Shahin Jabbari, Jichen Zhu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations

Abstract

Algorithmic fairness is an essential requirement as AI becomes integrated in society. In the case of social applications where AI distributes resources, algorithms often must make decisions that will benefit a subset of users, sometimes repeatedly or exclusively, while attempting to maximize specific outcomes. How should we design such systems to serve users more fairly? This paper explores this question in the case where a group of users works toward a shared goal in a social exergame called Step Heroes. We identify adverse outcomes in traditional multi-armed bandits (MABs) and formalize the Greedy Bandit Problem. We then propose a solution based on a new type of fairness-aware multi-armed bandit, Shapley Bandits. It uses the Shapley Value for increasing overall player participation and intervention adherence rather than the maximization of total group output, which is traditionally achieved by favoring only high-performing participants. We evaluate our approach via a user study (n=46). Our results indicate that our Shapley Bandits effectively mediates the Greedy Bandit Problem and achieves better user retention and motivation across the participants.

Original languageEnglish (US)
Title of host publicationIUI 2023 - Proceedings of the 28th International Conference on Intelligent User Interfaces
PublisherAssociation for Computing Machinery
Pages322-336
Number of pages15
ISBN (Electronic)9798400701061
DOIs
StatePublished - Mar 27 2023
Event28th International Conference on Intelligent User Interfaces, IUI 2023 - Sydney, Australia
Duration: Mar 27 2023Mar 31 2023

Publication series

NameInternational Conference on Intelligent User Interfaces, Proceedings IUI

Conference

Conference28th International Conference on Intelligent User Interfaces, IUI 2023
Country/TerritoryAustralia
CitySydney
Period3/27/233/31/23

All Science Journal Classification (ASJC) codes

  • Software
  • Human-Computer Interaction

Fingerprint

Dive into the research topics of 'Improving Fairness in Adaptive Social Exergames via Shapley Bandits'. Together they form a unique fingerprint.

Cite this