Algorithmic Bias: An Integrative Review and Scope for Future Research

Abstract

Today Artificial Intelligence and Machine Learning (ML) algorithms are influencing various aspects of human life, for instance - healthcare, loan provision, education, recruitment, and so on. But these systems are facing the issue of algorithmic bias, they can potentially generate socially biased outcomes, and they can enhance inequalities in the workplace as well as in society, even when there is no intention of doing so. The current literature on algorithmic bias is progressing in various directions in the absence of a robust theoretical foundation. Therefore, there is a requirement for a consolidation to provide a comprehensive and up-to-date summary of research in the area. This study presents an integrative review of the current body of literature on algorithmic bias, considering the diverse domains, samples, and methodologies employed in previous studies. This analysis highlights multiple gaps in the algorithmic bias domain. These gaps comprise definitional issues, insufficient theoretical foundations, thematic tensions, and inconsistencies in current literature. A potential future research avenue is proposed, which consists of a collection of various themes and research gaps. Also, a theoretical framework is provided that might serve as a guiding principle for future research in the domain of algorithmic bias.