Estimating Value Preferences in a Hybrid Participatory System

Luciano C. Siebert*, Enrico Liscio, Pradeep K. Murukannaiah, Lionel Kaptein, Shannon Spruit, Jeroen Van Den Hoven, Catholijn Jonker

*Corresponding author for this work

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

3 Citations (Scopus)
48 Downloads (Pure)

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.
Original languageEnglish
Title of host publicationHHAI2022
Subtitle of host publicationAugmenting Human Intellect - Proceedings of the 1st International Conference on Hybrid Human-Artificial Intelligence
EditorsStefan Schlobach, Maria Perez-Ortiz, Myrthe Tielman
PublisherIOS Press
Pages114-127
Number of pages14
ISBN (Electronic)9781643683089
DOIs
Publication statusPublished - 2022
Event1st International Conference on Hybrid Human-Artificial Intelligence, HHAI 2022 - Amsterdam, Netherlands
Duration: 13 Jun 202217 Jun 2022

Publication series

NameFrontiers in Artificial Intelligence and Applications
Volume354
ISSN (Print)0922-6389

Conference

Conference1st International Conference on Hybrid Human-Artificial Intelligence, HHAI 2022
Country/TerritoryNetherlands
CityAmsterdam
Period13/06/2217/06/22

Keywords

  • participatory systems
  • responsible AI
  • Value alignment

Fingerprint

Dive into the research topics of 'Estimating Value Preferences in a Hybrid Participatory System'. Together they form a unique fingerprint.

Cite this