Towards Algorithmic Transparency: A Diversity Perspective
This work addresses bias and fairness issues in AI for society, but it is incremental as it builds on existing transparency research by integrating diversity.
The paper tackles the problem of algorithmic bias by highlighting the overlooked role of diversity in algorithmic transparency, proposing a conceptual framework to characterize and apply transparency solutions in algorithmic systems.
As the role of algorithmic systems and processes increases in society, so does the risk of bias, which can result in discrimination against individuals and social groups. Research on algorithmic bias has exploded in recent years, highlighting both the problems of bias, and the potential solutions, in terms of algorithmic transparency (AT). Transparency is important for facilitating fairness management as well as explainability in algorithms; however, the concept of diversity, and its relationship to bias and transparency, has been largely left out of the discussion. We reflect on the relationship between diversity and bias, arguing that diversity drives the need for transparency. Using a perspective-taking lens, which takes diversity as a given, we propose a conceptual framework to characterize the problem and solution spaces of AT, to aid its application in algorithmic systems. Example cases from three research domains are described using our framework.