Towards trustworthy AI systems: A human-AI interaction study

Simple item page
dc.contributor.authorNguyen, Thuy-Trinhen
dc.contributor.authorPan, Shan L.en
dc.contributor.authorNguyen, Hoang D.en
dc.date.accessioned2024-05-29T13:44:46Z
dc.date.available2024-05-29T13:44:46Z
dc.date.issued2024en
dc.description.abstractThe partnership between humans and artificial intelligence (AI) has transformed decisionmaking and brought significant improvements in various fields. However, the complex operations of AI remain a black box in many cases, causing a lack of transparency that affects human trust in AI systems, particularly in high-risk scenarios. To address this issue, multi-agent systems have been proposed, where humans and AI interact and collaborate to achieve a better outcome and trust level. This study investigates the dynamic human-AI interaction and how it affects trust. We proposed design guidelines for interactive, trustworthy AI systems and developed two prototype versions to facilitate fake profile screening on online social networks. The study reports a mean trust score of 3.84/5 between humans and AI, despite a significant difference in their decisions on 2,142 user profiles. The results offer comprehensive insights into information systems involving human-AI interactions and underscore the increasing necessity for trustworthy AI.en
dc.description.statusPeer revieweden
dc.description.versionAccepted Versionen
dc.format.mimetypeapplication/pdfen
dc.identifier.citationNguyen, T.-T., Pan, S. L. and Nguyen, H. D. (2024) 'Towards trustworthy AI systems: A human-AI interaction study’, Pacific Asia Conference on Information Systems (PACIS 2024), Ho Chi Minh City, Vietnam, 1-5 July.en
dc.identifier.endpage16en
dc.identifier.startpage1en
dc.identifier.urihttps://hdl.handle.net/10468/15951
dc.language.isoenen
dc.relation.ispartofPacific Asia Conference on Information Systems (PACIS 2024), Ho Chi Minh City, Vietnam, 1-5 July.en
dc.rights© 2024, the Authors.en
dc.subjectTrustworthy AIen
dc.subjectHuman-AI interactionen
dc.subjectInteractive AI systemsen
dc.subjectFake identity detectionen
dc.subjectSocial screeningen
dc.titleTowards trustworthy AI systems: A human-AI interaction studyen
dc.typeConference itemen
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
2024_PACIS_Trustworthy_AI.pdf
Size:
881.96 KB
Format:
Adobe Portable Document Format
Description:
Accepted Version
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
2.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Computer Science - Conference Items
Insight Centre for Data Analytics - Conference Items