Leveraging Actionable Explanations to Improve People’s Reactions to AI-based Decisions
Markus Langer, Isabel Valera · 2024
This paper explores the role of explanations in mitigating negative reactions among people affected by AI-based decisions. While existing research focus-es primarily on user perspectives, this study addresses the unique needs of people affected by AI-based decisions. Drawing on justice theory and the al-gorithmic recourse literature, we propose that actionability is a primary need of people affected by AI-based decisions. Thus, we expected that more ac-tionable explanations – that is, explanations that guide people on how to ad-dress negative outcomes – would elicit more favorable reactions than feature relevance explanations or no explanations. In a within-participants experi-ment, participants (N = 138) imagined being loan applicants and were in-formed that their loan application had been rejected by AI-based systems at five different banks. Participants received either no explanation, feature rele-vance explanations, or actionable explanations for this decision. Additional-ly, we varied the degree of actionability of the features mentioned in the ex-planations to explore whether features that are more actionable (i.e., reduce the amount of loan) lead to additional positive effects on people’s reactions compared to less actionable features (i.e., increase your income). We found that providing any explanation led to more favorable reactions, and that ac-tionable explanations led to more favorable reactions than feature relevance explanations. However, focusing on the supposedly more actionable feature led to comparably more negative effects possibly due to our specific context of application. We discuss the crucial role that perceived actionability may play for people affected by AI-based decisions as well as the nuanced effects that focusing on different features in explanations may have.