Agent EXPRI: Licence to Explain

Research output: Chapter in Book/Report/Conference proceedingConference paperpeer-review

51 Downloads (Pure)

Abstract

Online social networks are known to lack adequate multi-user privacy support. In this paper we present EXPRI, an agent architecture that aims to assist users in managing multi-user privacy conflicts. By considering the personal utility of sharing content and the individually preferred moral values of each user involved in the conflict, EXPRI identifies the best collaborative solution by applying practical reasoning techniques. Such techniques provide the agent with the cognitive process that is necessary for explainability. Furthermore, the knowledge gathered during the practical reasoning process allows EXPRI to engage in contrastive explanations.
Original languageEnglish
Title of host publication2nd International Workshop on EXplainable TRansparent Autonomous Agents and Multi-Agent Systems
Publication statusAccepted/In press - 2020

Keywords

  • Privacy
  • Explainable Agents
  • Practical Reasoning

Fingerprint

Dive into the research topics of 'Agent EXPRI: Licence to Explain'. Together they form a unique fingerprint.

Cite this