Calibrating trust toward an autonomous image classifier

Ingram, M., Moreton, R., Gancz, B. and Pollick, F. (2021) Calibrating trust toward an autonomous image classifier. Technology, Mind, and Behavior, 2(1), (doi: 10.1037/tmb0000032)

[img] Text
235049.pdf - Published Version
Available under License Creative Commons Attribution Non-commercial No Derivatives.



Successful adoption of autonomous systems requires appropriate trust from human users, with trust calibrated to reflect true system performance. Autonomous image classifiers are one such example and can be used in a variety of settings to independently identify the contents of image data. We investigated users’ trust when collaborating with an autonomous image classifier system (AICS) that we created using the AlexNet model (). Participants collaborated with the classifier during an image classification task in which the classifier provided labels that either correctly or incorrectly described the contents of images. This task was complicated by the quality of the images processed by the human classifier team: 50% of the trials featured images that were cropped and blurred, thereby partially obscuring their contents. Across 160 single-image trials, we examined trust toward the classifier, while we also looked at how participants complied with the classifier by accepting or rejecting the labels it provided. Furthermore, we investigated whether trust toward the classifier could be improved by increasing the transparency of the classifier’s interface, by displaying system confidence information (SCI) in three different ways, which were compared to a control interface without confidence information. Results showed that trust toward the classifier was primarily based on system performance, yet this also was influenced by the quality of the images and individual differences among participants. While participants typically preferred classifier interfaces that presented confidence information, it did not appear to improve participants’ trust toward the classifier.

Item Type:Articles
Glasgow Author(s) Enlighten ID:Ingram, Martin and Pollick, Professor Frank
Authors: Ingram, M., Moreton, R., Gancz, B., and Pollick, F.
College/School:College of Science and Engineering > School of Psychology
Journal Name:Technology, Mind, and Behavior
Publisher:American Psychological Association
ISSN (Online):2689-0208
Published Online:11 June 2021
Copyright Holders:Copyright © 2021 The Authors
First Published:First published in Technology, Mind, and Behavior 2(1)
Publisher Policy:Reproduced under a Creative Commons License
Data DOI:10.5255/UKDA-SN-854151

University Staff: Request a correction | Enlighten Editors: Update this record

Project CodeAward NoProject NamePrincipal InvestigatorFunder's NameFunder RefLead Dept
303166Scottish Graduate School Science Doctoral Training Partnership (DTP)Mary Beth KneafseyEconomic and Social Research Council (ESRC)ES/P000681/1SS - Academic & Student Administration