A Methodological Framework and Questionnaire for Investigating Perceived Algorithmic Fairness

TL;DR

This paper investigates perceptions of algorithmic fairness among Bangladeshi users using mixed methods, revealing cultural influences on fairness, transparency, and accountability in AI systems.

Contribution

It introduces a culturally aware framework and questionnaire for assessing perceived algorithmic fairness in non-Western contexts.

Findings

Nuanced attitudes toward human oversight and explanations

Cultural factors significantly influence fairness perceptions

Highlights need for culturally sensitive AI design

Abstract

This study explores perceptions of fairness in algorithmic decision-making among users in Bangladesh through a comprehensive mixed-methods approach. By integrating quantitative survey data with qualitative interview insights, we examine how cultural, social, and contextual factors influence users' understanding of fairness, transparency, and accountability in AI systems. Our findings reveal nuanced attitudes toward human oversight, explanation mechanisms, and contestability, highlighting the importance of culturally aware design principles for equitable and trustworthy algorithmic systems. These insights contribute to ongoing discussions on algorithmic fairness by foregrounding perspectives from a non-Western context, thus broadening the global dialogue on ethical AI deployment.