Export Publication

The publication can be exported in the following formats: APA (American Psychological Association) reference format, IEEE (Institute of Electrical and Electronics Engineers) reference format, BibTeX and RIS.

Export Reference (APA) 
Duarte, R., Correia, F., Arriaga, P. & Paiva, A. (2023). AI trust: Can explainable AI enhance warranted trust?. Human Behavior and Emerging Technologies. 2023
Export Reference (IEEE) 
R. D. Duarte et al.,  "AI trust: Can explainable AI enhance warranted trust?", in Human Behavior and Emerging Technologies, vol. 2023, 2023
Export BibTeX 
@article{duarte2023_1716220415706,
	author = "Duarte, R. and Correia, F. and Arriaga, P. and Paiva, A.",
	title = "AI trust: Can explainable AI enhance warranted trust?",
	journal = "Human Behavior and Emerging Technologies",
	year = "2023",
	volume = "2023",
	number = "",
	doi = "10.1155/2023/4637678",
	url = "https://www.hindawi.com/journals/hbet/contents/"
}
Export RIS 
TY  - JOUR
TI  - AI trust: Can explainable AI enhance warranted trust?
T2  - Human Behavior and Emerging Technologies
VL  - 2023
AU  - Duarte, R.
AU  - Correia, F.
AU  - Arriaga, P.
AU  - Paiva, A.
PY  - 2023
SN  - 2578-1863
DO  - 10.1155/2023/4637678
UR  - https://www.hindawi.com/journals/hbet/contents/
AB  - Explainable artificial intelligence (XAI), known to produce explanations so that predictions from AI models can be understood, is commonly used to mitigate possible AI mistrust. The underlying premise is that the explanations of the XAI models enhance AI trust. However, such an increase may depend on many factors. This article examined how trust in an AI recommendation system is affected by the presence of explanations, the performance of the system, and the level of risk. Our experimental study, conducted with 215 participants, has shown that the presence of explanations increases AI trust, but only in certain conditions. AI trust was higher when explanations with feature importance were provided than with counterfactual explanations. Moreover, when the system performance is not guaranteed, the use of explanations seems to lead to an overreliance on the system. Lastly, system performance had a stronger impact on trust, compared to the effects of other factors (explanation and risk).
ER  -