Explainable Artificial Intelligence: Objectives, Stakeholders, and Future Research Opportunities

被引:215
作者
Meske, Christian [1 ,2 ]
Bunde, Enrico [1 ,2 ]
Schneider, Johannes [3 ]
Gersch, Martin [4 ]
机构
[1] Free Univ Berlin, Dept Informat Syst, D-14195 Berlin, Germany
[2] Einstein Ctr Digital Future, D-14195 Berlin, Germany
[3] Univ Liechtenstein, Inst Informat Syst, Vaduz, Liechtenstein
[4] Free Univ Berlin, Einstein Ctr Digital Future Well Digital Entrepre, Dept Informat Syst, Berlin, Germany
关键词
Artificial Intelligence; explainability; accountability; transparency; trust; managing AI; DECISION-SUPPORT-SYSTEM; THEORETICAL FOUNDATIONS; AUTOMATION BIAS; BLACK-BOX; EXPLANATIONS;
D O I
10.1080/10580530.2020.1849465
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Artificial Intelligence (AI) has diffused into many areas of our private and professional life. In this research note, we describe exemplary risks of black-box AI, the consequent need for explainability, and previous research on Explainable AI (XAI) in information systems research. Moreover, we discuss the origin of the term XAI, generalized XAI objectives, and stakeholder groups, as well as quality criteria of personalized explanations. We conclude with an outlook to future research on XAI.
引用
收藏
页码:53 / 63
页数:11
相关论文
共 86 条
[1]   Trends and Trajectories for Explainable, Accountable and Intelligible Systems: An HCI Research Agenda [J].
Abdul, Ashraf ;
Vermeulen, Jo ;
Wang, Danding ;
Lim, Brian ;
Kankanhalli, Mohan .
PROCEEDINGS OF THE 2018 CHI CONFERENCE ON HUMAN FACTORS IN COMPUTING SYSTEMS (CHI 2018), 2018,
[2]   Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI) [J].
Adadi, Amina ;
Berrada, Mohammed .
IEEE ACCESS, 2018, 6 :52138-52160
[3]   Electronic Markets and current general research [J].
Alt, Rainer .
ELECTRONIC MARKETS, 2018, 28 (02) :123-128
[4]  
[Anonymous], 2019, Digital Economy and Society Index Report 2019. P, P6
[5]  
Arnold V, 2006, MIS QUART, V30, P79
[6]  
Arnold V., 1998, ADV ACCOUNTING BEHAV, V1, P175
[7]  
Berente N, 2019, MIS Quarterly, V45, P1, DOI [10.25300/MISQ/2021/16274, DOI 10.25300/MISQ/2021/16274]
[8]  
Binns R., 2018, Proceedings of Machine Learning Research, V81, P1, DOI DOI 10.48550/ARXIV.1712.03586
[9]   AI surpasses humans at six-player poker [J].
Blair, Alan ;
Saffidine, Abdallah .
SCIENCE, 2019, 365 (6456) :864-865
[10]  
Bohmann Tilo, 2014, Wirtschaftsinformatik, V56, P83, DOI 10.1007/s11576-014-0406-6