Man’s morality is a result of an inductive constructionist process. Input into the process are moral dilemmata or their storylike representations, its output are general patterns allowing to classify as moral or immoral even the dilemmas which were not represented in the initial training corpus. Moral inference process can be simulated by machine learning algorithms and can be based upon detection and extraction of morally relevant features. Supervised or semisupervised approaches should be used by those aiming to simulate parent -> child or teacher -> student information transfer processes in artificial agents. Preexisting models of inference e.g. the grammar inference models in the domain of computational linguistics can be exploited to build a moral induction model. Historical data, mythology or folklore could serve as a basis of the training corpus which could be subsequently significantly extended by a crowdsourcing method exploiting the webbased « Completely Automated Moral Turing test to tell Computers and Humans Apart ».
Keywords: moral induction model, autonomous artificial agent, induction of morality,
grammar inference, moral Turing test, corpus-based machine learning, morally relevant features, oracle machine, moral grammar, semantic enrichment, CAMTCHA
(also backed-up at
https://dev.kyberia.cz/k/2ttjd )
presented at the conference of International Association of Computing and Philosophy, 2013, Maryland, USA.