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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

To ensure accountability and mitigate harm, it is critical that diversestakeholders can interrogate black-box automated systems and find informationthat is understandable, relevant, and useful to them. In this paper, we eschewprior expertise- and role-based categorizations of interpretabilitystakeholders in favor of a more granular framework that decouples stakeholders'knowledge from their interpretability needs. We characterize stakeholders bytheir formal, instrumental, and personal knowledge and how it manifests in thecontexts of machine learning, the data domain, and the general milieu. Weadditionally distill a hierarchical typology of stakeholder needs thatdistinguishes higher-level domain goals from lower-level interpretabilitytasks. In assessing the descriptive, evaluative, and generative powers of ourframework, we find our more nuanced treatment of stakeholders reveals gaps andopportunities in the interpretability literature, adds precision to the designand comparison of user studies, and facilitates a more reflexive approach toconducting this research.

Beyond Expertise and Roles: A Framework to Characterize the Stakeholders of Interpretable Machine Learning and their Needs