BlocklyBias: a visual programming language for bias identification in AI data

In the current landscape of Artificial Intelligence (AI), bias has emerged as a central concern in both public discourse and scientific inquiry. In today’s rapidly evolving landscape, marked by increasing complexity and challenges, there is a growing need to address the issue of biases and discrimination that can be exacerbated by algorithms. Biases can infiltrate data collection, whether conducted by humans or systems they design, highlighting the multifaceted nature of this challenge. Consequently, addressing this issue from diverse perspectives is imperative, extending its reach beyond technical domains to include stakeholders from various backgrounds. This paper aims to illustrate how the democratization of the data analysis process – specifically regarding intersectional biases – can be achieved through the use of Visual Programming Languages (VPLs). By reducing the technical entry barrier, fostering an understanding of bias, and providing mitigation strategies, this research introduces BlocklyBias, a platform founded on VPL principles. BlocklyBias serves as a foundational stepping stone for future improvements, as a tool to explore and resolve bias-related challenges in data analysis. Through this study, we seek to bridge the gap between technical and non-technical stakeholders, fostering a collaborative approach to bias mitigation in AI.