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

By Christian Meske, Enrico Bunde, Johannes Schneider, Martin Gersch. Information systems management, 2020

336 citations recorded by the source corpus.

ABSTRACT 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.

Subfields: Artificial Intelligence, Health Informatics, Safety Research

View Paper: https://www.semanticscholar.org/paper/96b2d31d5a4ef9c683ecf000b109be8d8e70b20d

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Longo Luca
2. Lars Kunze
3. Elena Hernández-Pereira
4. Eduardo Mosqueira-Rey
5. Á. Fernández-Leal
6. José Bobes-Bascarán
7. David Alonso-Ríos
8. Helena Webb

In Health Informatics

1. Longo Luca
2. Javier Del Ser

In Safety Research

1. Marina Jirotka
2. Longo Luca

Citations in the corpus

• Human-in-the-loop machine learning: a state of the art (2022, background): “Sometimes these reviews offer perspectives that do not always coincide as occurs with XAI goals which are classified differently in recent review papers (Barredo Arrieta et al. 2020; Minh et al. 2021; Meske et al. 2022; Das and Rad 2020).”
• Explanations in Autonomous Driving: A Survey (2021, background): “Personalisation is seen to be crucial for the generation of intelligible or understandable explanations [67], [68], [69].”
• Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directions (2023, background): “While some concepts are universal, such as ‘every car has tires and tires are round’, others are more subjective or differ among stakeholders and cultures and depend on domain knowledge, that is, knowledge related to training data [234].”