Michael Guckert
A Conceptual Framework for Establishing Trust in Real World Intelligent Systems
Guckert, Michael; Gumpfer, Nils; Hannig, Jennifer; Keller, Till; Urquhart, Neil
Abstract
Intelligent information systems that contain emergent elements often encounter trust problems because results do not get sufficiently explained and the procedure itself can not be fully retraced. This is caused by a control flow depending either on stochastic elements or on the structure and relevance of the input data. Trust in such algorithms can be established by letting users interact with the system so that they can explore results and find patterns that can be compared with their expected solution. Reflecting features and patterns of human understanding of a domain against algorithmic results can create awareness of such patterns and may increase the trust that a user has in the solution. If expectations are not met, close inspection can be used to decide whether a solution conforms to the expectations or whether it goes beyond the expected. By either accepting or rejecting a solution, the user's set of expectations evolves and a learning process for the users is established. In this paper we present a conceptual framework that reflects and supports this process. The framework is the result of an analysis of two exemplary case studies from two different disciplines with information systems that assist experts in their complex tasks.
Citation
Guckert, M., Gumpfer, N., Hannig, J., Keller, T., & Urquhart, N. (2021). A Conceptual Framework for Establishing Trust in Real World Intelligent Systems. Cognitive Systems Research, 68, 143-155. https://doi.org/10.1016/j.cogsys.2021.04.001
Journal Article Type | Article |
---|---|
Acceptance Date | Apr 6, 2021 |
Online Publication Date | Apr 28, 2021 |
Publication Date | 2021-08 |
Deposit Date | Apr 8, 2021 |
Publicly Available Date | Oct 29, 2022 |
Journal | Cognitive Systems Research |
Print ISSN | 1389-0417 |
Publisher | Elsevier |
Peer Reviewed | Peer Reviewed |
Volume | 68 |
Pages | 143-155 |
DOI | https://doi.org/10.1016/j.cogsys.2021.04.001 |
Keywords | Intelligent Systems, AI, Trust, Explainable AI, Knowledge Management, Knowledge Patterns |
Public URL | http://researchrepository.napier.ac.uk/Output/2759756 |
Files
A Conceptual Framework For Establishing Trust In Real World Intelligent Systems
(11.9 Mb)
PDF
Publisher Licence URL
http://creativecommons.org/licenses/by/4.0/
Copyright Statement
This is an open access article under the CC BY license: http://creativecommons.org/licenses/by/4.0/
You might also like
The British Rail Total Operations Processing System And the Birth of Telematics
(2024)
Journal Article
Evolving Staff Training Schedules using an Extensible Fitness Function and a Domain Specific Language
(2024)
Presentation / Conference Contribution
The stuff we swim in: Regulation alone will not lead to justifiable trust in AI
(2023)
Journal Article
Extending AGADE Traffic To Simulate Auctions In Shared Mobility Services
(2023)
Presentation / Conference Contribution
Improving the size and quality of MAP-Elites containers via multiple emitters and decoders for urban logistics
(2023)
Presentation / Conference Contribution