Engineering user-centered explanations to query answers in ontology-driven socio-technical systems

The role of explanations in intelligent systems has in the last few years entered the spotlight as AI-based solutions appear in an ever-growing set of applications. Though data-driven (or machine learning) techniques are often used as examples of how opaque (also called black box) approaches can lea...

Descripción completa

Detalles Bibliográficos
Autores: Teze, Juan Carlos L., Paredes, Jose Nicolas, Martinez,Maria Vanina, Simari, Gerardo Ignacio
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2024
País:España
Institución:Consejo Superior de Investigaciones Científicas (CSIC)
Repositorio:DIGITAL.CSIC. Repositorio Institucional del CSIC
OAI Identifier:oai:digital.csic.es:10261/387022
Acceso en línea:http://hdl.handle.net/10261/387022
Access Level:acceso abierto
Palabra clave:Ontological languages
Socio-technical systems
Explainable Artificial Intelligence
Hate speech in social platforms
id ES_8982e08067de18cbbdb9cc306e0861e7
oai_identifier_str oai:digital.csic.es:10261/387022
network_acronym_str ES
network_name_str España
repository_id_str
spelling Engineering user-centered explanations to query answers in ontology-driven socio-technical systemsTeze, Juan Carlos L.Paredes, Jose NicolasMartinez,Maria VaninaSimari, Gerardo IgnacioOntological languagesSocio-technical systemsExplainable Artificial IntelligenceHate speech in social platformsThe role of explanations in intelligent systems has in the last few years entered the spotlight as AI-based solutions appear in an ever-growing set of applications. Though data-driven (or machine learning) techniques are often used as examples of how opaque (also called black box) approaches can lead to problems such as bias and general lack of explainability and interpretability, in reality these features are difficult to tame in general, even for approaches that are based on tools typically considered to be more amenable, like knowledge-based formalisms. In this paper, we continue a line of research and development towards building tools that facilitate the implementation of explainable and interpretable hybrid intelligent socio-technical systems, focusing on features that users can leverage to build explanations to their queries. In particular, we present the implementation of a recently-proposed application framework (and make available its source code) for developing such systems, and explore user-centered mechanisms for building explanations based both on the kinds of explanations required (such as counterfactual, contextual, etc.) and the inputs used for building them (coming from various sources, such as the knowledge base and lower-level data-driven modules). In order to validate our approach, we develop two use cases, one as a running example for detecting hate speech in social platforms and the other as an extension that also contemplates cyberbullying scenarios.This work was funded in part by Universidad Nacional del Sur (UNS) under grants PGI 24/ZN34 and PGI 24/N056, Secretaría de Investigación Científica y Tecnológica FCEN–UBA (RESCS-2020-345-E-UBA-REC), Universidad Nacional de Entre Ríos under grant PDTS-UNER 7066, CONICET under grants PIP 11220200101408CO and PIP 11220210100577CO, and Agencia Nacional de Promoción Científica y Tecnológica, Argentina under grants PICT-2018-0475 (PRH-2014-0007) and PICT-2020 SERIE A-01481. Finally, we are grateful to the reviewers of this paper, who provided extensive and constructive comments that have significantly improved our work.CPeer reviewedSage PublicationsUniversidad Nacional del SurUniversidad Nacional de Entre Ríos (Argentina)Agencia Nacional de Promoción Científica y Tecnológica (Argentina)202520252024info:eu-repo/semantics/articlehttp://purl.org/coar/resource_type/c_6501Publisher's versioninfo:eu-repo/semantics/publishedVersionapplication/pdfhttp://hdl.handle.net/10261/387022reponame:DIGITAL.CSIC. Repositorio Institucional del CSICinstname:Consejo Superior de Investigaciones Científicas (CSIC)InglésThe underlying dataset has been published as supplementary material of the article in the publisher platform at DOI https://doi.org/10.3233/SW-233297https://doi.org/10.3233/SW-233297Noinfo:eu-repo/semantics/openAccessoai:digital.csic.es:10261/3870222026-05-22T06:33:51Z
dc.title.none.fl_str_mv Engineering user-centered explanations to query answers in ontology-driven socio-technical systems
title Engineering user-centered explanations to query answers in ontology-driven socio-technical systems
spellingShingle Engineering user-centered explanations to query answers in ontology-driven socio-technical systems
Teze, Juan Carlos L.
Ontological languages
Socio-technical systems
Explainable Artificial Intelligence
Hate speech in social platforms
title_short Engineering user-centered explanations to query answers in ontology-driven socio-technical systems
title_full Engineering user-centered explanations to query answers in ontology-driven socio-technical systems
title_fullStr Engineering user-centered explanations to query answers in ontology-driven socio-technical systems
title_full_unstemmed Engineering user-centered explanations to query answers in ontology-driven socio-technical systems
title_sort Engineering user-centered explanations to query answers in ontology-driven socio-technical systems
dc.creator.none.fl_str_mv Teze, Juan Carlos L.
Paredes, Jose Nicolas
Martinez,Maria Vanina
Simari, Gerardo Ignacio
author Teze, Juan Carlos L.
author_facet Teze, Juan Carlos L.
Paredes, Jose Nicolas
Martinez,Maria Vanina
Simari, Gerardo Ignacio
author_role author
author2 Paredes, Jose Nicolas
Martinez,Maria Vanina
Simari, Gerardo Ignacio
author2_role author
author
author
dc.contributor.none.fl_str_mv Universidad Nacional del Sur
Universidad Nacional de Entre Ríos (Argentina)
Agencia Nacional de Promoción Científica y Tecnológica (Argentina)
dc.subject.none.fl_str_mv Ontological languages
Socio-technical systems
Explainable Artificial Intelligence
Hate speech in social platforms
topic Ontological languages
Socio-technical systems
Explainable Artificial Intelligence
Hate speech in social platforms
description The role of explanations in intelligent systems has in the last few years entered the spotlight as AI-based solutions appear in an ever-growing set of applications. Though data-driven (or machine learning) techniques are often used as examples of how opaque (also called black box) approaches can lead to problems such as bias and general lack of explainability and interpretability, in reality these features are difficult to tame in general, even for approaches that are based on tools typically considered to be more amenable, like knowledge-based formalisms. In this paper, we continue a line of research and development towards building tools that facilitate the implementation of explainable and interpretable hybrid intelligent socio-technical systems, focusing on features that users can leverage to build explanations to their queries. In particular, we present the implementation of a recently-proposed application framework (and make available its source code) for developing such systems, and explore user-centered mechanisms for building explanations based both on the kinds of explanations required (such as counterfactual, contextual, etc.) and the inputs used for building them (coming from various sources, such as the knowledge base and lower-level data-driven modules). In order to validate our approach, we develop two use cases, one as a running example for detecting hate speech in social platforms and the other as an extension that also contemplates cyberbullying scenarios.
publishDate 2024
dc.date.none.fl_str_mv 2024
2025
2025
dc.type.none.fl_str_mv info:eu-repo/semantics/article
http://purl.org/coar/resource_type/c_6501
Publisher's version
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/10261/387022
url http://hdl.handle.net/10261/387022
dc.language.none.fl_str_mv Inglés
language_invalid_str_mv Inglés
dc.relation.none.fl_str_mv The underlying dataset has been published as supplementary material of the article in the publisher platform at DOI https://doi.org/10.3233/SW-233297
https://doi.org/10.3233/SW-233297
No
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Sage Publications
publisher.none.fl_str_mv Sage Publications
dc.source.none.fl_str_mv reponame:DIGITAL.CSIC. Repositorio Institucional del CSIC
instname:Consejo Superior de Investigaciones Científicas (CSIC)
instname_str Consejo Superior de Investigaciones Científicas (CSIC)
reponame_str DIGITAL.CSIC. Repositorio Institucional del CSIC
collection DIGITAL.CSIC. Repositorio Institucional del CSIC
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869412631869128704
score 15,811543

Similares en LA Referencia