Leveraging Visual Languages to Foster User Participation in Designing Trustworthy Machine Learning Systems: A Comparative Study

In the era of ubiquitous Artificial Intelligence (AI), Machine Learning (ML) systems have emerged as pivotal in advancing societal progress. Yet, their complexity often requires the expertise of professionals, presenting an entry barrier for less-experienced computing practitioners. In the realm of Human-Centered AI (HCAI), ongoing research is developing new approaches to engage users via intuitive interfaces in the design of ML-based systems. For example, Visual Programming Languages (VPLs) and no-code platforms offer user-friendly experiences by avoiding complex computational operations. However, literature on VPL-based tools for novices reveals a gap: many tools offer limited interpretability approaches or are overly complex for easy customization. To address this gap, we developed the PyFlowML prototype, an open-source, flow-based programming tool with a focus on Explainable AI (XAI). This study aims to set a benchmark in the field by comparing PyFlowML with KNIME, a similar tool known for its usability among domain specialists. Our results show that domain specialists perceive flow-based language tools as valuable. This study highlights the potential of VPL-based tools to make the design of trustworthy ML-based systems more inclusive, thereby contributing to the advancement of AI democratization.