Joining metadata and textual features to advise administrative courts decisions

Detalhes bibliográficos
Autor(a) principal: Mentzingen, Hugo
Data de Publicação: 2023
Outros Autores: Antonio, Nuno, Lobo, Victor
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: http://hdl.handle.net/10362/149493
Resumo: Mentzingen, H., Antonio, N., & Lobo, V. (2024). Joining metadata and textual features to advise administrative courts decisions: a cascading classifier approach. Artificial Intelligence and Law, 32(1), 201-230. https://doi.org/10.1007/s10506-023-09348-9
id RCAP_e76e67fbda60ff5282c69a89290a15ee
oai_identifier_str oai:run.unl.pt:10362/149493
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling Joining metadata and textual features to advise administrative courts decisionsa cascading classifier approachAdministrative decision predictionCascade generalizationLegal assistanceMachine learningNatural language processingLawArtificial IntelligenceSDG 16 - Peace, Justice and Strong InstitutionsMentzingen, H., Antonio, N., & Lobo, V. (2024). Joining metadata and textual features to advise administrative courts decisions: a cascading classifier approach. Artificial Intelligence and Law, 32(1), 201-230. https://doi.org/10.1007/s10506-023-09348-9Decisions of regulatory government bodies and courts affect many aspects of citizens’ lives. These organizations and courts are expected to provide timely and coherent decisions, although they struggle to keep up with the increasing demand. The ability of machine learning (ML) models to predict such decisions based on past cases under similar circumstances was assessed in some recent works. The dominant conclusion is that the prediction goal is achievable with high accuracy. Nevertheless, most of those works do not consider important aspects for ML models that can impact performance and affect real-world usefulness, such as consistency, out-of-sample applicability, generality, and explainability preservation. To our knowledge, none considered all those aspects, and no previous study addressed the joint use of metadata and text-extracted variables to predict administrative decisions. We propose a predictive model that addresses the abovementioned concerns based on a two-stage cascade classifier. The model employs a first-stage prediction based on textual features extracted from the original documents and a second-stage classifier that includes proceedings’ metadata. The study was conducted using time-based cross-validation, built on data available before the predicted judgment. It provides predictions as soon as the decision date is scheduled and only considers the first document in each proceeding, along with the metadata recorded when the infringement is first registered. Finally, the proposed model provides local explainability by preserving visibility on the textual features and employing the SHapley Additive exPlanations (SHAP). Our findings suggest that this cascade approach surpasses the standalone stages and achieves relatively high Precision and Recall when both text and metadata are available while preserving real-world usefulness. With a weighted F1 score of 0.900, the results outperform the text-only baseline by 1.24% and the metadata-only baseline by 5.63%, with better discriminative properties evaluated by the receiver operating characteristic and precision-recall curves.NOVA Information Management School (NOVA IMS)Information Management Research Center (MagIC) - NOVA Information Management SchoolRUNMentzingen, HugoAntonio, NunoLobo, Victor2023-02-20T22:20:32Z2024-032024-03-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article30application/pdfhttp://hdl.handle.net/10362/149493eng0924-8463PURE: 53862943https://doi.org/10.1007/s10506-023-09348-9info:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2024-03-11T05:31:23Zoai:run.unl.pt:10362/149493Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T03:53:45.940881Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse
dc.title.none.fl_str_mv Joining metadata and textual features to advise administrative courts decisions
a cascading classifier approach
title Joining metadata and textual features to advise administrative courts decisions
spellingShingle Joining metadata and textual features to advise administrative courts decisions
Mentzingen, Hugo
Administrative decision prediction
Cascade generalization
Legal assistance
Machine learning
Natural language processing
Law
Artificial Intelligence
SDG 16 - Peace, Justice and Strong Institutions
title_short Joining metadata and textual features to advise administrative courts decisions
title_full Joining metadata and textual features to advise administrative courts decisions
title_fullStr Joining metadata and textual features to advise administrative courts decisions
title_full_unstemmed Joining metadata and textual features to advise administrative courts decisions
title_sort Joining metadata and textual features to advise administrative courts decisions
author Mentzingen, Hugo
author_facet Mentzingen, Hugo
Antonio, Nuno
Lobo, Victor
author_role author
author2 Antonio, Nuno
Lobo, Victor
author2_role author
author
dc.contributor.none.fl_str_mv NOVA Information Management School (NOVA IMS)
Information Management Research Center (MagIC) - NOVA Information Management School
RUN
dc.contributor.author.fl_str_mv Mentzingen, Hugo
Antonio, Nuno
Lobo, Victor
dc.subject.por.fl_str_mv Administrative decision prediction
Cascade generalization
Legal assistance
Machine learning
Natural language processing
Law
Artificial Intelligence
SDG 16 - Peace, Justice and Strong Institutions
topic Administrative decision prediction
Cascade generalization
Legal assistance
Machine learning
Natural language processing
Law
Artificial Intelligence
SDG 16 - Peace, Justice and Strong Institutions
description Mentzingen, H., Antonio, N., & Lobo, V. (2024). Joining metadata and textual features to advise administrative courts decisions: a cascading classifier approach. Artificial Intelligence and Law, 32(1), 201-230. https://doi.org/10.1007/s10506-023-09348-9
publishDate 2023
dc.date.none.fl_str_mv 2023-02-20T22:20:32Z
2024-03
2024-03-01T00:00:00Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://hdl.handle.net/10362/149493
url http://hdl.handle.net/10362/149493
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv 0924-8463
PURE: 53862943
https://doi.org/10.1007/s10506-023-09348-9
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv 30
application/pdf
dc.source.none.fl_str_mv reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron:RCAAP
instname_str Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron_str RCAAP
institution RCAAP
reponame_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
collection Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository.name.fl_str_mv Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
repository.mail.fl_str_mv
_version_ 1799138127372091392

Registros relacionados