Explaining Decision-Making Algorithms through UI

TLDR

Algorithms increasingly drive important societal decisions, yet their opacity hampers transparency and can provoke negative emotions. The study aims to derive design principles for explanation interfaces that convey how decision‑making algorithms operate, to aid organizations and support users' right to explanation. An online experiment with 199 participants compared various explanation interfaces for a university admissions algorithm, measuring objective and self‑reported understanding. Both interactive and white‑box explanations improve comprehension, with interactive explanations yielding greater gains at the cost of more time, while trust in algorithmic decisions remains unchanged by interface type or comprehension level.

Abstract

Increasingly, algorithms are used to make important decisions across society. However, these algorithms are usually poorly understood, which can reduce transparency and evoke negative emotions. In this research, we seek to learn design principles for explanation interfaces that communicate how decision-making algorithms work, in order to help organizations explain their decisions to stakeholders, or to support users' "right to explanation". We conducted an online experiment where 199 participants used different explanation interfaces to understand an algorithm for making university admissions decisions. We measured users' objective and self-reported understanding of the algorithm. Our results show that both interactive explanations and "white-box" explanations (i.e. that show the inner workings of an algorithm) can improve users' comprehension. Although the interactive approach is more effective at improving comprehension, it comes with a trade-off of taking more time. Surprisingly, we also find that users' trust in algorithmic decisions is not affected by the explanation interface or their level of comprehension of the algorithm.