Questioning the AI: Informing Design Practices for Explainable AI User Experiences
Вопросы к ИИ: развитие практик проектирования пользовательского опыта для объяснимого искусственного интеллекта
2020-04-21
SCID: 54.1/g85b4nb7
Discuss with AI
AI user experiencesUX design practitionersXAI question bankexplainable AIuser-centered XAI
Figures from the paper
Abstract (AI)
A surge of interest in explainable AI (XAI) has led to a vast collection of algorithmic work on the topic. While many recognize the necessity to incorporate explainability features in AI systems, how to address real-world user needs for understanding AI remains an open question. By interviewing 20 UX and design practitioners working on various AI products, we seek to identify gaps between the current XAI algorithmic work and practices to create explainable AI products. To do so, we develop an algorithm-informed XAI question bank in which user needs for explainability are represented as prototypical questions users might ask about the AI, and use it as a study probe. Our work contributes insights into the design space of XAI, informs efforts to support design practices in this space, and identifies opportunities for future XAI work. We also provide an extended XAI question bank and discuss how it can be used for creating user-centered XAI.
Key Findings
1
Interviews with 20 UX and design practitioners revealed gaps between algorithm-focused XAI research and the needs of real-world explainable AI product design.
2
The findings inform design practices and identify opportunities for future research connecting algorithmic XAI work with user needs.
3
The question bank served as a study probe for identifying practical insights and opportunities within the design space of explainable AI.
4
The study developed an algorithm-informed XAI question bank representing explainability needs as prototypical questions users might ask about AI systems.
5
The work provides an extended XAI question bank and discusses its use for supporting user-centered explainable AI design.
Research Object
explainable AI (XAI) products and their user experiences
Research Subject
UX and design practices for addressing users’ explainability needs, including gaps between algorithmic XAI research and real-world product design
Publication Details
Publication Date
2020-04-21
Journal
Publisher
ISSN
Cited by
960
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai10
A Unified Approach to Interpreting Model Predictions2017
Greedy function approximation: A gradient boosting machine.2001
"Why Should I Trust You?": Explaining the Predictions of Any Classifier2016
Learning Deep Features for Discriminative Localization2016
Towards A Rigorous Science of Interpretable Machine Learning2017
Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI)2018
Machine Learning Interpretability: A Survey on Methods and Metrics2019
Power to the People: The Role of Humans in Interactive Machine Learning2014
Designing Theory-Driven User-Centric Explainable AI2019
A Survey of Methods for Explaining Black Box Models2018