Explainability for experts: A design framework for making algorithms supporting expert decisions more explainable

Algorithmic decision support systems are widely applied in domains ranging from healthcare to journalism. To ensure that these systems are fair and accountable, it is essential that humans can maintain meaningful agency, understand and oversee algorithmic processes. Explainability is often seen as a...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Auste Simkute, Ewa Luger, Bronwyn Jones, Michael Evans, Rhianne Jones
Formato:	article
Lenguaje:	EN
Publicado:	Elsevier 2021
Materias:	Explainability Decision support systems Journalism Human-in-the-loop Expertise Information technology T58.5-58.64
Acceso en línea:	https://doaj.org/article/c67e658e63724db0bf46090d18fc599c
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:c67e658e63724db0bf46090d18fc599c
record_format	dspace
spelling	oai:doaj.org-article:c67e658e63724db0bf46090d18fc599c2021-11-30T04:17:49ZExplainability for experts: A design framework for making algorithms supporting expert decisions more explainable2666-659610.1016/j.jrt.2021.100017https://doaj.org/article/c67e658e63724db0bf46090d18fc599c2021-10-01T00:00:00Zhttp://www.sciencedirect.com/science/article/pii/S266665962100010Xhttps://doaj.org/toc/2666-6596Algorithmic decision support systems are widely applied in domains ranging from healthcare to journalism. To ensure that these systems are fair and accountable, it is essential that humans can maintain meaningful agency, understand and oversee algorithmic processes. Explainability is often seen as a promising mechanism for enabling human-in-the-loop, however, current approaches are ineffective and can lead to various biases. We argue that explainability should be tailored to support naturalistic decision-making and sensemaking strategies employed by domain experts and novices. Based on cognitive psychology and human factors literature review we map potential decision-making strategies dependant on expertise, risk and time dynamics and propose the conceptual Expertise, Risk and Time Explainability framework, intended to be used as explainability design guidelines. Finally, we present a worked example in journalism to illustrate the applicability of our framework in practice.Auste SimkuteEwa LugerBronwyn JonesMichael EvansRhianne JonesElsevierarticleExplainabilityDecision support systemsJournalismHuman-in-the-loopExpertiseInformation technologyT58.5-58.64ENJournal of Responsible Technology, Vol 7, Iss , Pp 100017- (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Explainability Decision support systems Journalism Human-in-the-loop Expertise Information technology T58.5-58.64
spellingShingle	Explainability Decision support systems Journalism Human-in-the-loop Expertise Information technology T58.5-58.64 Auste Simkute Ewa Luger Bronwyn Jones Michael Evans Rhianne Jones Explainability for experts: A design framework for making algorithms supporting expert decisions more explainable
description	Algorithmic decision support systems are widely applied in domains ranging from healthcare to journalism. To ensure that these systems are fair and accountable, it is essential that humans can maintain meaningful agency, understand and oversee algorithmic processes. Explainability is often seen as a promising mechanism for enabling human-in-the-loop, however, current approaches are ineffective and can lead to various biases. We argue that explainability should be tailored to support naturalistic decision-making and sensemaking strategies employed by domain experts and novices. Based on cognitive psychology and human factors literature review we map potential decision-making strategies dependant on expertise, risk and time dynamics and propose the conceptual Expertise, Risk and Time Explainability framework, intended to be used as explainability design guidelines. Finally, we present a worked example in journalism to illustrate the applicability of our framework in practice.
format	article
author	Auste Simkute Ewa Luger Bronwyn Jones Michael Evans Rhianne Jones
author_facet	Auste Simkute Ewa Luger Bronwyn Jones Michael Evans Rhianne Jones
author_sort	Auste Simkute
title	Explainability for experts: A design framework for making algorithms supporting expert decisions more explainable
title_short	Explainability for experts: A design framework for making algorithms supporting expert decisions more explainable
title_full	Explainability for experts: A design framework for making algorithms supporting expert decisions more explainable
title_fullStr	Explainability for experts: A design framework for making algorithms supporting expert decisions more explainable
title_full_unstemmed	Explainability for experts: A design framework for making algorithms supporting expert decisions more explainable
title_sort	explainability for experts: a design framework for making algorithms supporting expert decisions more explainable
publisher	Elsevier
publishDate	2021
url	https://doaj.org/article/c67e658e63724db0bf46090d18fc599c
work_keys_str_mv	AT austesimkute explainabilityforexpertsadesignframeworkformakingalgorithmssupportingexpertdecisionsmoreexplainable AT ewaluger explainabilityforexpertsadesignframeworkformakingalgorithmssupportingexpertdecisionsmoreexplainable AT bronwynjones explainabilityforexpertsadesignframeworkformakingalgorithmssupportingexpertdecisionsmoreexplainable AT michaelevans explainabilityforexpertsadesignframeworkformakingalgorithmssupportingexpertdecisionsmoreexplainable AT rhiannejones explainabilityforexpertsadesignframeworkformakingalgorithmssupportingexpertdecisionsmoreexplainable
_version_	1718406772612399104

Explainability for experts: A design framework for making algorithms supporting expert decisions more explainable

Ejemplares similares