Table 6

Future research agenda concerning the goals and objectives of AI system explanations for end users

Goal/objectiveFuture research directionSource
UnderstandabilityInvestigate different groups of end users and their ability to understand AI system explanationsCheng et al. (2019) 
Elucidate and determine the desired levels of understanding of AI systems of different stakeholdersThis study
TrustworthinessInvestigate if involving humans in the loop of AI decision making can increase trust in AI systemsCheng et al. (2019) 
Investigate emotional and cognitive factors involved in trust such as surprise, confusion and cognitive dissonanceYin et al. (2019) 
Determine how various explanation types influence the resulting trust toward the AI systemThis study
TransparencyInvestigate the link between transparency and trustEiband et al. (2018) 
Investigate how information disclosure and presentation are linked to end users' perceived transparency of the explanationsThis study
ControllabilityConnect the goal of controllability to understandability, transparency, trustworthiness and fairness of the systemThis study
FairnessApproach the issue from various psychology of justice theories such as interactional justiceBinns et al. (2018) 
Studies regarding the fairness of AI system explanations could focus on how well end users understand the real behavior of the system based on provided explanationsThis study

or Create an Account

Close subscription notice
Close access options