Human Centered Approaches and Taxonomies for Explainable Artificial Intelligence

Recent interest within the research community related to explainable artificial intelligence (XAI) has led to a profuse amount of literature on the subject. Those who wish to tackle the domain from an HCI focus may be presented with overwhelming material, most of which does not pertain to human aspects of XAI. Taxonomies can serve to categorize a subject into topic areas and distill content into an overview of the field. This late breaking work intends to help those within the HCI community with a focus on XAI to understand relevant aspects of human centered XAI. We also present a taxonomy which can be used when categorizing real world XAI to identify gaps in XAI methods and predict future areas of research. Lastly, we introduce a novel aspect, practical XAI evaluation methods from a human centered perspective allowing for more effective evaluation of the AI – human interaction.