The AI-DEC: A Card-based Design Method for User-centered AI Explanations

TL;DR

The paper introduces AI-DEC, a card-based design method that helps end-users co-design AI explanations tailored to their needs, improving user engagement and understanding in real-world applications.

Contribution

It presents a novel, structured design method for user-centered AI explanations, addressing the gap in engaging end-users in explanation design.

Findings

AI-DEC supported diverse explanation designs in co-design sessions.

Users tailored explanations to their performance and autonomy needs.

The method facilitated understanding of AI systems in real-world contexts.

Abstract

Increasing evidence suggests that many deployed AI systems do not sufficiently support end-user interaction and information needs. Engaging end-users in the design of these systems can reveal user needs and expectations, yet effective ways of engaging end-users in the AI explanation design remain under-explored. To address this gap, we developed a design method, called AI-DEC, that defines four dimensions of AI explanations that are critical for the integration of AI systems -- communication content, modality, frequency, and direction -- and offers design examples for end-users to design AI explanations that meet their needs. We evaluated this method through co-design sessions with workers in healthcare, finance, and management industries who regularly use AI systems in their daily work. Findings indicate that the AI-DEC effectively supported workers in designing explanations that accommodated diverse levels of performance and autonomy needs, which varied depending on the AI system's workplace role and worker values. We discuss the implications of using the AI-DEC for the user-centered design of AI explanations in real-world systems.