Designing Human-Centered AI Tools with Interactive Visualization

Abstract

Human-centered AI (HCAI), rather than replacing the human, puts the user in the driver's seat of so-called human-centered AI-infused tools (HCAI tools): interactive software tools that amplify, augment, empower, and enhance human performance using AI models. In this dissertation, I discuss how interactive visualization can be a key enabling technology for creating such human-centered AI tools. Visualization has already been shown to be a fundamental component in explainable AI models, and coupling this with data-driven, semantic, and unified interaction feedback loops will enable a human-centered approach for bridging AI models and human users. To validate this approach, I at first interviewed HCI, AI, and Visualization experts to define the characteristics of HCAI tools. I then discuss the design and development process of four HCAI tools powered by visualization. I conclude by outlining the design guidelines learned from the design process of the tools and research directions for designing future HCAI tools.