Human-Computer Interaction and Explainability: Intersection and Terminology

Abstract

Human-computer interaction (HCI) is generally considered the broader domain encompassing the study of the relationships between humans and types of technological artifacts or systems. Explainable AI (xAI) is involved in HCI to have humans better understand computers or AI systems which fosters, as a consequence, better interaction. The term “explainability” is sometimes used interchangeably with other closely related terms such as interpretability or understandability. The same can be said for the term “interaction”. It is a very broad way to describe the relationship between humans and technologies, which is why it is often replaced or completed by more precise terms like cooperation, collaboration, teaming, symbiosis, and integration. In the same vein, the technologies are represented by several terms like computer, machine, AI, agent, and robot. However, each of these terms (technologies and relationships) has its specificity and properties which need to be clearly defined. Currently, the definitions of these various terms are not well established in the literature, and their usage in various contexts is ambiguous. The goals of this paper are threefold: First, clarify the terminology in the HCI domain representing the technologies and their relationships with humans. A few concepts specific to xAI are also clarified. Second, highlight the role that xAI plays or can play in the HCI domain. Third, study the evolution and tendency of the usage of explainability and interpretability with the HCI terminology throughout the years and highlight the observations in the last three years.