Print Email Facebook Twitter Estimating Value Preferences in a Hybrid Participatory System Title Estimating Value Preferences in a Hybrid Participatory System Author Cavalcante Siebert, L. (TU Delft Interactive Intelligence) Liscio, E. (TU Delft Interactive Intelligence) Murukannaiah, P.K. (TU Delft Interactive Intelligence) Kaptein, Lionel (Student TU Delft) Spruit, Shannon (Populytics B.V) van den Hoven, M.J. (TU Delft Ethics & Philosophy of Technology) Jonker, C.M. (TU Delft Interactive Intelligence) Contributor Schlobach, Stefan (editor) Perez-Ortiz, Maria (editor) Tielman, Myrthe (editor) Date 2022 Abstract We propose methods for an AI agent to estimate the value preferences of individuals in a hybrid participatory system, considering a setting where participants make choices and provide textual motivations for those choices. We focus on situations where there is a conflict between participants' choices and motivations, and operationalize the philosophical stance that 'valuing is deliberatively consequential.' That is, if a user's choice is based on a deliberation of value preferences, the value preferences can be observed in the motivation the user provides for the choice. Thus, we prioritize the value preferences estimated from motivations over the value preferences estimated from choices alone. We evaluate the proposed methods on a dataset of a large-scale survey on energy transition. The results show that explicitly addressing inconsistencies between choices and motivations improves the estimation of an individual's value preferences. The proposed methods can be integrated in a hybrid participatory system, where artificial agents ought to estimate humans' value preferences to pursue value alignment. Subject participatory systemsresponsible AIValue alignment To reference this document use: http://resolver.tudelft.nl/uuid:4215fdce-8d78-48b9-b5a0-884bd2b36626 DOI https://doi.org/10.3233/FAIA220193 Publisher IOS Press ISBN 9781643683089 Source HHAI2022: Augmenting Human Intellect - Proceedings of the 1st International Conference on Hybrid Human-Artificial Intelligence Event 1st International Conference on Hybrid Human-Artificial Intelligence, HHAI 2022, 2022-06-13 → 2022-06-17, Amsterdam, Netherlands Series Frontiers in Artificial Intelligence and Applications, 0922-6389, 354 Part of collection Institutional Repository Document type conference paper Rights © 2022 L. Cavalcante Siebert, E. Liscio, P.K. Murukannaiah, Lionel Kaptein, Shannon Spruit, M.J. van den Hoven, C.M. Jonker Files PDF FAIA_354_FAIA220193.pdf 452.29 KB Close viewer /islandora/object/uuid:4215fdce-8d78-48b9-b5a0-884bd2b36626/datastream/OBJ/view