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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Strategies based on Explainable Artificial Intelligence - XAI have promotedbetter human interpretability of the results of black box machine learningmodels. The XAI measures being currently used (Ciu, Dalex, Eli5, Lofo, Shap,and Skater) provide various forms of explanations, including global rankings ofrelevance of attributes. Current research points to the need for furtherstudies on how these explanations meet the Interpretability Expectations ofhuman experts and how they can be used to make the model even more transparentwhile taking into account specific complexities of the model and dataset beinganalyzed, as well as important human factors of sensitive real-worldcontexts/problems. Intending to shed light on the explanations generated by XAImeasures and their interpretabilities, this research addresses a real-worldclassification problem related to homicide prediction, duly endorsed by thescientific community, replicated its proposed black box model and used 6different XAI measures to generate explanations and 6 different human expertsto generate what this research referred to as Interpretability Expectations -IE. The results were computed by means of comparative analysis andidentification of relationships among all the attribute ranks produced, and~49% concordance was found among attributes indicated by means of XAI measuresand human experts, ~41% exclusively by XAI measures and ~10% exclusively byhuman experts. The results allow for answering: "Do the different XAI measuresgenerate similar explanations for the proposed problem?", "Are theinterpretability expectations generated among different human expertssimilar?", "Do the explanations generated by XAI measures meet theinterpretability expectations of human experts?" and "Can InterpretabilityExplanations and Expectations work together?", all of which concerning thecontext of homicide prediction.

Black Box Model Explanations and the Human Interpretability Expectations -- An Analysis in the Context of Homicide Prediction