Designer-User Communication for XAI: An epistemological approach to discuss XAI design
This work addresses the problem of improving communication between designers and end-users in XAI design, which is incremental as it builds on existing frameworks by extending focus beyond data scientists.
The paper tackles the challenge of discussing explainable AI (XAI) features with diverse stakeholders, particularly end-users, by proposing an epistemological approach using the Signifying Message as a conceptual tool to structure and facilitate these discussions early in the design process, as demonstrated in a healthcare AI system case study.
Artificial Intelligence is becoming part of any technology we use nowadays. If the AI informs people's decisions, the explanation about AI's outcomes, results, and behavior becomes a necessary capability. However, the discussion of XAI features with various stakeholders is not a trivial task. Most of the available frameworks and methods for XAI focus on data scientists and ML developers as users. Our research is about XAI for end-users of AI systems. We argue that we need to discuss XAI early in the AI-system design process and with all stakeholders. In this work, we aimed at investigating how to operationalize the discussion about XAI scenarios and opportunities among designers and developers of AI and its end-users. We took the Signifying Message as our conceptual tool to structure and discuss XAI scenarios. We experiment with its use for the discussion of a healthcare AI-System.