Towards Human-centered Explainable AI: User Studies for Model Explanations

by   Yao Rong, et al.

Explainable AI (XAI) is widely viewed as a sine qua non for ever-expanding AI research. A better understanding of the needs of XAI users, as well as human-centered evaluations of explainable models are both a necessity and a challenge. In this paper, we explore how HCI and AI researchers conduct user studies in XAI applications based on a systematic literature review. After identifying and thoroughly analyzing 85 core papers with human-based XAI evaluations over the past five years, we categorize them along the measured characteristics of explanatory methods, namely trust, understanding, fairness, usability, and human-AI team performance. Our research shows that XAI is spreading more rapidly in certain application domains, such as recommender systems than in others, but that user evaluations are still rather sparse and incorporate hardly any insights from cognitive or social sciences. Based on a comprehensive discussion of best practices, i.e., common models, design choices, and measures in user studies, we propose practical guidelines on designing and conducting user studies for XAI researchers and practitioners. Lastly, this survey also highlights several open research directions, particularly linking psychological science and human-centered XAI.


page 1

page 2

page 3

page 4


Questioning the AI: Informing Design Practices for Explainable AI User Experiences

A surge of interest in explainable AI (XAI) has led to a vast collection...

Explainable AI: Beware of Inmates Running the Asylum Or: How I Learnt to Stop Worrying and Love the Social and Behavioural Sciences

In his seminal book `The Inmates are Running the Asylum: Why High-Tech P...

Designing Disaggregated Evaluations of AI Systems: Choices, Considerations, and Tradeoffs

Several pieces of work have uncovered performance disparities by conduct...

Towards Better User Requirements: How to Involve Human Participants in XAI Research

Human-Center eXplainable AI (HCXAI) literature identifies the need to ad...

Connecting Algorithmic Research and Usage Contexts: A Perspective of Contextualized Evaluation for Explainable AI

Recent years have seen a surge of interest in the field of explainable A...

Towards a Learner-Centered Explainable AI: Lessons from the learning sciences

In this short paper, we argue for a refocusing of XAI around human learn...

Towards User-Centered Metrics for Trustworthy AI in Immersive Cyberspace

AI plays a key role in current cyberspace and future immersive ecosystem...

Please sign up or login with your details

Forgot password? Click here to reset