English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Explainable AI (XAI) is widely viewed as a sine qua non for ever-expanding AIresearch. A better understanding of the needs of XAI users, as well ashuman-centered evaluations of explainable models are both a necessity and achallenge. In this paper, we explore how HCI and AI researchers conduct userstudies in XAI applications based on a systematic literature review. Afteridentifying and thoroughly analyzing 97core papers with human-based XAIevaluations over the past five years, we categorize them along the measuredcharacteristics of explanatory methods, namely trust, understanding, usability,and human-AI collaboration performance. Our research shows that XAI isspreading more rapidly in certain application domains, such as recommendersystems than in others, but that user evaluations are still rather sparse andincorporate hardly any insights from cognitive or social sciences. Based on acomprehensive discussion of best practices, i.e., common models, designchoices, and measures in user studies, we propose practical guidelines ondesigning 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.

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