An Approach to Computing Ethics

To make ethics computable, we've adopted an approach to ethics that involves considering multiple prima facie duties in deciding how one should act in an ethical dilemma. We believe this approach is more likely to capture the complexities of ethical decision making than a single, absolute-duty ethical theory. However, it requires a decision procedure for determining the ethically correct action when the duties give conflicting advice. To solve this problem, we employ inductive-logic programming to enable a machine to abstract information from ethical experts' intuitions about particular ethical dilemmas, to create a decision principle. We've tested our method in the MedEthEx proof-of-concept system, using a type of ethical dilemma that involves 18 possible combinations of three prima facie duties. The system needed just four training cases to create an ethically significant decision principle that covered the remaining cases. This article is part of a special issue on Machine Ethics.