Table 1

The 5Cs—opposing effects of AI explainability

Opposing effectsDescriptionKey sources
ComprehensibilityUnderstandability of what explainability of AI means to different stakeholders, especially laypeopleAdadi and Berrada (2018), Arrieta et al. (2020), De Graaf and Malle (2017), Harper (2019), Holzinger et al. (2019), Miller (2019), Ntoutsi et al. (2020), Páez (2019) 
ConductThe innovativeness and performance of AI systems and their explainabilityD'Acquisto (2020), Diez-Olivan et al. (2019), Gunning and Aha (2019), Gunning et al. (2019), Robbins (2019a), Silver et al. (2016) 
ConfidentialityConfidentiality, security and safety risks due to the explainability of AI systemsArrieta et al. (2020), Holzinger et al. (2019), Tóth (2019) 
CompletenessConsequences due to AI logic that cannot be proved or explainedArrieta et al. (2020), D'Acquisto (2020), Silver et al. (2016) 
Confidence in AIOverconfidence in AI outcomes vs. mistrust of AI due to its explanationBertino et al. (2019), Harper (2019), Mittelstadt et al. (2016), Pieters (2011) 

or Create an Account

Close subscription notice
Close access options