Scientific journal paper Q1
AI trust: Can explainable AI enhance warranted trust?
Regina de Brito Duarte (Duarte, R.); Filipa Correia (Correia, F.); Patrícia Arriaga (Arriaga, P.); Ana Paiva (Paiva, A.);
Journal Title
Human Behavior and Emerging Technologies
Year (definitive publication)
2023
Language
English
Country
United States of America
More Information
Web of Science®

Times Cited: 2

(Last checked: 2024-11-20 00:57)

View record in Web of Science®


: 0.5
Scopus

Times Cited: 4

(Last checked: 2024-11-21 08:50)

View record in Scopus


: 0.6
Google Scholar

Times Cited: 7

(Last checked: 2024-11-17 22:57)

View record in Google Scholar

Abstract
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).
Acknowledgements
--
Keywords
Artificial intelligence (AI),Trust,Explainable AI,Risk
  • Computer and Information Sciences - Natural Sciences
  • Psychology - Social Sciences
Funding Records
Funding Reference Funding Entity
LA/P/0083/2020 Fundação para a Ciência e a Tecnologia
UIDB/50021/ 2020 Fundação para a Ciência e a Tecnologia
UIDP/50009/2020 Fundação para a Ciência e a Tecnologia
H2020-ICT-48-2020/952026 Comissão Europeia
TAILORH2020-ICT-48-2020/952215 Comissão Europeia

With the objective to increase the research activity directed towards the achievement of the United Nations 2030 Sustainable Development Goals, the possibility of associating scientific publications with the Sustainable Development Goals is now available in Ciência-IUL. These are the Sustainable Development Goals identified by the author(s) for this publication. For more detailed information on the Sustainable Development Goals, click here.