Abstract
We conducted a study to explore the effect of different types of Artificial intelligence (AI) explanations on the human trust in AI systems. An in person user study was conducted (n = 7) and the trust condition was induced by varying the accuracy of AI response. The human trust was measured by surveys administered after each trial. The participants physiological data was also collected during the experiment. Our results show that image based explanations induced higher level of arousal in the participants, and the participants preferred image based explanations. We also found that the AI response accuracy had an effect on the user acceptance of AI’s decision in the following trial. We also found that Photoplethysmography results had statistically significant correlation with the level of trust. The implications of this study are that AI performance and type of explanations both have an effect on the level of user trust in AI. Also this work could be extended to develop an objective measure of trust using physiological data.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Markus, A.F., Kors, J.A., Rijnbeek, P.R.: The role of explainability in creating trustworthy artificial intelligence for health care: a comprehensive survey of the terminology, design choices, and evaluation strategies. J. Biomed. Inform. 113, 103655 (2021)
Chatzimparmpas, A., Martins, R.M., Jusufi, I., Kucher, K., Rossi, F., Kerren, A.: The state of the art in enhancing trust in machine learning models with the use of visualizations. Comput. Graph. Forum 39(3), 713–756 (2020)
Yin, M., Wortman Vaughan, J., Wallach, H.: Understanding the effect of accuracy on trust in machine learning models. In: Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems, pp. 1–12, May 2019
Israelsen, B.W., Ahmed, N.R.: “Dave...I can assure you ...that it’s going to be all right ...” a definition, case for, and survey of algorithmic assurances in human-autonomy trust relationships. ACM Comput. Surv. 51, 6, Article no. 113 (2019), 37 p. https://doi.org/10.1145/3267338
Yang, F., Huang, Z., Scholtz, J., Arendt, D.L.: How do visual explanations foster end users’ appropriate trust in machine learning? In: Proceedings of the 25th International Conference on Intelligent User Interfaces, pp. 189–201, March 2020
Mitkidis, P., McGraw, J.J., Roepstorff, A., Wallot, S.: Building trust: Heart rate synchrony and arousal during joint action increased by public goods game. Physiol. Behav. 149, 101–106 (2015)
Merrill, N., Cheshire, C.: Trust your heart: assessing cooperation and trust with biosignals in computer-mediated interactions. In: Proceedings of the 2017 ACM Conference on Computer Supported Cooperative Work and Social Computing, pp. 2–12, February 2017
Ditzen, B., Schaer, M., Gabriel, B., Bodenmann, G., Ehlert, U., Heinrichs, M.: Intranasal oxytocin increases positive communication and reduces cortisol levels during couple conflict. Biol. Psychiatry 65(9), 728–731 (2009)
Morris, D.M., Erno, J.M., Pilcher, J.J.: Electrodermal response and automation trust during simulated self-driving car use. In: Proceedings of the Human Factors and Ergonomics Society Annual Meeting, vol. 61, no. 1, pp. 1759–1762. SAGE Publications, Los Angeles, September 2017
Zak, P.J.: The neuroscience of trust. Harv. Bus. Rev. 95(1), 84–90 (2017)
McKnight, D.H., Choudhury, V., Kacmar, C.: Developing and validating trust measures for e-commerce: an integrative typology. Inf. Syst. Res. 13(3), 334–359 (2002). Modified to cater to trust in AI instead of trust in people. Disposition to trust inventory
Pham, N.T., Lee, J.W., Kwon, G.R., Park, C.S.: Hybrid image-retrieval method for image-splicing validation. Symmetry 11(1), 83 (2019)
Madsen, M., Gregor, S.D.: Measuring human-computer trust (2000)
Acknowledgements
We would like to acknowledge the contribution to the trust testbed development by Robert Dillon and Noor Khattak. We would also like to thank Hien Tran and Miguel Cuahuizo for their contributions to the data analysis phase of the project.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Bui, L., Pezzola, M., Bandara, D. (2023). How Do AI Explanations Affect Human-AI Trust?. In: Degen, H., Ntoa, S. (eds) Artificial Intelligence in HCI. HCII 2023. Lecture Notes in Computer Science(), vol 14050. Springer, Cham. https://doi.org/10.1007/978-3-031-35891-3_12
Download citation
DOI: https://doi.org/10.1007/978-3-031-35891-3_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-35890-6
Online ISBN: 978-3-031-35891-3
eBook Packages: Computer ScienceComputer Science (R0)