Document Type

Conference Paper

Rights

Available under a Creative Commons Attribution Non-Commercial Share Alike 4.0 International Licence

Disciplines

Computer Sciences

Publication Details

CENTRIC 2022 : The Fifteenth International Conference on Advances in Human-oriented and Personalized Mechanisms, Technologies, and Services, Lisbon

https://www.thinkmind.org/index.php?view=article&articleid=centric_2022_1_10_30002

Abstract

Artificial Intelligence (AI) is playing an important role in society including how vital, often life changing decisions are made. For this reason, interest in Explainable Artificial Intelligence (XAI) has grown in recent years as a means of revealing the processes and operations contained within what is often described as a black box, an often-opaque system whose decisions are difficult to understand by the end user. This paper presents the results of a design thinking workshop with 20 participants (computer science and graphic design students) where we sought to investigate users' mental models when interacting with AI systems. Using two personas, participants were asked to empathise with two end users of an AI driven recruitment system, identify pain points in a user’s experience and ideate on possible solutions to these pain points. These tasks were used to explore the user’s understanding of AI systems, the intelligibility of AI systems and how the inner workings of these systems might be explained to end users. We discovered that visual feedback, analytics, and comparisons, feature highlighting in conjunction with factual, counterfactual and principal reasoning explanations could be used to improve user’s mental models of AI systems.

DOI

https://doi.org/10.21427/1875-6019

Funder

TU Dublin

Creative Commons License

Creative Commons Attribution 4.0 International License
This work is licensed under a Creative Commons Attribution 4.0 International License.

Download
Contact the Author


Share

COinS