Explain to Whom? From User Feedback to Actionable Explanations

As machine learning algorithms increasingly influence crucial life decisions, such as lending or job selection, providing actionable explanations becomes paramount. These explanations must clarify the reasoning behind an AI’s decision and empower individuals to alter these outcomes. This study clarifies the concept of actionability within explainable AI (XAI) by evaluating the effectiveness of non-direct and directive counterfactual explanations. Non-directive explanations detail the changes needed for a different decision, while directive explanations provide specific actions toward achieving a desired result. Our research assesses the actionability of these explanation types by utilizing existing actionability instruments complemented by open-ended queries. Our quantitative and qualitative analyses converge on the importance of clarity, relevance, feasibility, and user-centricity in explanations, highlighting how these factors significantly influence users’ ability to understand and act upon AI-generated explanations. This study suggests enriching.