{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T06:52:08Z","timestamp":1773298328840,"version":"3.50.1"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,2,18]],"date-time":"2023-02-18T00:00:00Z","timestamp":1676678400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,2,18]],"date-time":"2023-02-18T00:00:00Z","timestamp":1676678400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100005855","name":"Universidade Nova de Lisboa","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100005855","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Artif Intell Law"],"published-print":{"date-parts":[[2024,3]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Decisions of regulatory government bodies and courts affect many aspects of citizens\u2019 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\u2019 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.<\/jats:p>","DOI":"10.1007\/s10506-023-09348-9","type":"journal-article","created":{"date-parts":[[2023,2,19]],"date-time":"2023-02-19T02:14:41Z","timestamp":1676772881000},"page":"201-230","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Joining metadata and textual features to advise administrative courts decisions: a cascading classifier approach"],"prefix":"10.1007","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8538-1727","authenticated-orcid":false,"given":"Hugo","family":"Mentzingen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4801-2487","authenticated-orcid":false,"given":"Nuno","family":"Antonio","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0149-3367","authenticated-orcid":false,"given":"Victor","family":"Lobo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,2,18]]},"reference":[{"issue":"10","key":"9348_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.7717\/peerj-cs.93","volume":"2016","author":"N Aletras","year":"2016","unstructured":"Aletras N, Tsarapatsanis D, Preo\u0163iuc-Pietro D, Lampos V (2016) Predicting judicial decisions of the European court of human rights: a natural language processing perspective. PeerJ Comput Sci 2016(10):1\u201319. https:\/\/doi.org\/10.7717\/peerj-cs.93","journal-title":"PeerJ Comput Sci"},{"issue":"2","key":"9348_CR2","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1007\/s10506-020-09270-4","volume":"29","author":"A Bibal","year":"2021","unstructured":"Bibal A, Lognoul M, De Streel A, Fr\u00e9nay B (2021) Legal requirements on explainability in machine learning. Artif Intell Law 29(2):149\u2013169. https:\/\/doi.org\/10.1007\/s10506-020-09270-4","journal-title":"Artif Intell Law"},{"key":"9348_CR3","doi-asserted-by":"publisher","DOI":"10.5555\/1717171","author":"S Bird","year":"2009","unstructured":"Bird S, Klein E, Loper E (2009) Natural language processing with python. O\u2019Reilly Med. https:\/\/doi.org\/10.5555\/1717171","journal-title":"O\u2019Reilly Med"},{"issue":"4\u20135","key":"9348_CR4","doi-asserted-by":"publisher","first-page":"993","DOI":"10.1016\/b978-0-12-411519-4.00006-9","volume":"3","author":"DM Blei","year":"2003","unstructured":"Blei DM, Ng AY, Jordan MI (2003) Latent dirichlet allocation. J Mach Learn Res 3(4\u20135):993\u20131022. https:\/\/doi.org\/10.1016\/b978-0-12-411519-4.00006-9","journal-title":"J Mach Learn Res"},{"key":"9348_CR5","doi-asserted-by":"publisher","unstructured":"Brill E (1992) A simple rule-based part of speech tagger. In: Proceedings of the third conference on applied natural language processing. Association for Computational Linguistics. https:\/\/doi.org\/10.3115\/974499.974526","DOI":"10.3115\/974499.974526"},{"key":"9348_CR6","unstructured":"Browlee J (2018) How to reduce variance in a final machine learning model. Mach Learn Mast. https:\/\/machinelearningmastery.com\/how-to-reduce-model-variance\/"},{"key":"9348_CR7","doi-asserted-by":"publisher","unstructured":"Cer D, Yang Y, Kong SYI, Hua N, Limtiaco N, John SR, Constant N, Guajardo-C\u00e9spedes M, Yuan S, Tar C, Sung YH, Strope B, Kurzweil R (2018) Universal sentence encoder. In: EMNLP 2018\u2013conference on empirical methods in natural language processing: system demonstrations, Proceedings. https:\/\/doi.org\/10.18653\/v1\/d18-2029","DOI":"10.18653\/v1\/d18-2029"},{"key":"9348_CR8","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1613\/jair.953","volume":"16","author":"NV Chawla","year":"2002","unstructured":"Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP (2002) SMOTE: synthetic minority over-sampling technique. J Artif Intell Res 16:321\u2013357","journal-title":"J Artif Intell Res"},{"key":"9348_CR9","doi-asserted-by":"publisher","unstructured":"Chen DL, Eagel J (2017) Can machine learning help predict the outcome of asylum adjudications? In: Proceedings of the international conference on artificial intelligence and law, pp 237\u2013240. https:\/\/doi.org\/10.1145\/3086512.3086538","DOI":"10.1145\/3086512.3086538"},{"key":"9348_CR10","doi-asserted-by":"publisher","unstructured":"Chen T, Guestrin C (2016) XGBoost: a scalable tree boosting system. In: Proceedings of the 22nd ACM sigkdd international conference on knowledge discovery and data mining, pp 785\u2013794. https:\/\/doi.org\/10.1145\/2939672.2939785","DOI":"10.1145\/2939672.2939785"},{"key":"9348_CR11","doi-asserted-by":"publisher","unstructured":"Chen L (2009). Curse of dimensionality. In: Encyclopedia of database systems pp 545\u2013546. Springer. https:\/\/doi.org\/10.1007\/978-0-387-39940-9_133","DOI":"10.1007\/978-0-387-39940-9_133"},{"key":"9348_CR12","unstructured":"Devlin J, Chang MW, Lee K, Toutanova K (2019) BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL HLT 2019\u20132019 conference of the north american chapter of the association for computational linguistics: human language technologies\u2013proceedings of the conference, vol 1, pp 4171\u20134186. https:\/\/github.com\/tensorflow\/tensor2tensor"},{"issue":"7","key":"9348_CR13","doi-asserted-by":"publisher","first-page":"1895","DOI":"10.1162\/089976698300017197","volume":"10","author":"TG Dietterich","year":"1998","unstructured":"Dietterich TG (1998) Approximate statistical tests for comparing supervised classification learning algorithms. Neural Comput 10(7):1895\u20131923. https:\/\/doi.org\/10.1162\/089976698300017197","journal-title":"Neural Comput"},{"key":"9348_CR14","doi-asserted-by":"publisher","DOI":"10.1186\/s13173-014-0020-x","author":"ER Fonseca","year":"2015","unstructured":"Fonseca ER, Rosa JGL, Alu\u00edsio SM (2015) Evaluating word embeddings and a revised corpus for part-of-speech tagging in Portuguese. J Br Comput Soc. https:\/\/doi.org\/10.1186\/s13173-014-0020-x","journal-title":"J Br Comput Soc"},{"issue":"3","key":"9348_CR15","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1023\/A:1007652114878","volume":"41","author":"J Gama","year":"2000","unstructured":"Gama J, Brazdil P (2000) Cascade generalization. Mach Learn 41(3):315\u2013343. https:\/\/doi.org\/10.1023\/A:1007652114878","journal-title":"Mach Learn"},{"key":"9348_CR16","unstructured":"Herman-Saffar O (2020) Time based cross validation. Towards Data Science. https:\/\/towardsdatascience.com\/time-based-cross-validation-d259b13d42b8"},{"key":"9348_CR17","unstructured":"IAIS (2017) Insurance core principles. https:\/\/www.iaisweb.org\/file\/69922\/insurance-core-principles-updated-november-2017"},{"issue":"4","key":"9348_CR18","doi-asserted-by":"publisher","first-page":"e0174698","DOI":"10.1371\/journal.pone.0174698","volume":"12","author":"DM Katz","year":"2017","unstructured":"Katz DM, Bommarito MJ, Blackman J (2017) A general approach for predicting the behavior of the Supreme Court of the United States. Plos One 12(4):e0174698. https:\/\/doi.org\/10.1371\/journal.pone.0174698","journal-title":"Plos One"},{"key":"9348_CR19","unstructured":"Le Q, Mikolov T (2014) Distributed representations of sentences and documents. In: 31st International conference on machine learning, ICML vol 4, pp 2931\u20132939"},{"issue":"4","key":"9348_CR20","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1147\/rd.14.0309","volume":"1","author":"HP Luhn","year":"1957","unstructured":"Luhn HP (1957) A statistical approach to mechanized encoding and searching of literary information. IBM J Res Dev 1(4):309\u2013317. https:\/\/doi.org\/10.1147\/rd.14.0309","journal-title":"IBM J Res Dev"},{"key":"9348_CR21","unstructured":"Lundberg SM, Lee SI (2017) A unified approach to interpreting model predictions. In: Proceedings of the 31st international conference on neural information processing systems, pp 4768\u20134777"},{"key":"9348_CR22","unstructured":"Mabey B, English P (2015) pyLDAvis (2.1.2). https:\/\/pyldavis.readthedocs.io\/en\/latest\/"},{"issue":"2","key":"9348_CR23","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1007\/s10506-019-09255-y","volume":"28","author":"M Medvedeva","year":"2020","unstructured":"Medvedeva M, Vols M, Wieling M (2020) Using machine learning to predict decisions of the European court of human rights. Artif Intell Law 28(2):237\u2013266. https:\/\/doi.org\/10.1007\/s10506-019-09255-y","journal-title":"Artif Intell Law"},{"key":"9348_CR24","unstructured":"Mikolov T, Chen K, Corrado G, Dean J (2013) Distributed representations of words and phrases and their compositionality. In: NIPS\u201913: proceedings of the 26th international conference on neural information processing systems, vol 2, pp 3111\u20133119"},{"key":"9348_CR25","unstructured":"Nason S (2018) Administrative justice can make countries fairer and more equal\u2014if it is implemented properly. The Conversation. https:\/\/theconversation.com\/administrative-justice-can-make-countries-fairer-and-more-equal-if-it-is-implemented-properly-108238"},{"key":"9348_CR26","doi-asserted-by":"publisher","unstructured":"Orengo VM, Huyck C (2001) A stemming algorithm for the portuguese language. In: Proceedings 8th symposium on string processing and information retrieval, pp 186\u2013193. https:\/\/doi.org\/10.1109\/spire.2001.989755","DOI":"10.1109\/spire.2001.989755"},{"key":"9348_CR27","first-page":"2825","volume":"324","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V, VanderPlas J, Passos A, Cournapeau D, Brucher M, Perrot M, Duchesnay E (2011) Scikit-learn: machine learning in python. J Mach Learn Res 324:2825\u20132830","journal-title":"J Mach Learn Res"},{"key":"9348_CR28","doi-asserted-by":"publisher","unstructured":"Pennington J, Socher R, Manning CD (2014) GloVe: global vectors for word representation. In: EMNLP 2014\u20132014 conference on empirical methods in natural language processing, proceedings of the conference, pp 1532\u20131543. https:\/\/doi.org\/10.3115\/v1\/d14-1162","DOI":"10.3115\/v1\/d14-1162"},{"key":"9348_CR29","doi-asserted-by":"publisher","unstructured":"Pillai VG, Chandran LR (2020) Verdict prediction for indian courts using bag of words and convolutional neural network. In: Proceedings of the 3rd international conference on smart systems and inventive technology, ICSSIT 2020, pp 676\u2013683. https:\/\/doi.org\/10.1109\/ICSSIT48917.2020.9214278","DOI":"10.1109\/ICSSIT48917.2020.9214278"},{"key":"9348_CR30","unstructured":"Richardson L (2007) BeautifulSoup. https:\/\/www.crummy.com\/software\/BeautifulSoup\/"},{"issue":"4","key":"9348_CR31","doi-asserted-by":"publisher","first-page":"1150","DOI":"10.2307\/4099370","volume":"104","author":"TW Ruger","year":"2004","unstructured":"Ruger TW, Kim PT, Martin AD, Quinn KM (2004) The Supreme court forecasting project: legal and political science approaches to predicting supreme court decisionmaking. Columbia Law Rev 104(4):1150\u20131210. https:\/\/doi.org\/10.2307\/4099370","journal-title":"Columbia Law Rev"},{"key":"9348_CR32","unstructured":"Shinyama Y, Guglielmetti P, Marsman P (2019) pdfminer.six. https:\/\/github.com\/pdfminer\/pdfminer.six"},{"issue":"3","key":"9348_CR33","doi-asserted-by":"publisher","first-page":"643","DOI":"10.1007\/s10772-021-09820-4","volume":"24","author":"N Sivaranjani","year":"2021","unstructured":"Sivaranjani N, Jayabharathy J, Teja PC (2021) Predicting the supreme court decision on appeal cases using hierarchical convolutional neural network. Int J Speech Technol 24(3):643\u2013650. https:\/\/doi.org\/10.1007\/s10772-021-09820-4","journal-title":"Int J Speech Technol"},{"key":"9348_CR34","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1108\/00220410410560573","volume":"28","author":"K Sp\u00e4rck Jones","year":"1972","unstructured":"Sp\u00e4rck Jones K (1972) A statistical interpretation of term specificity and its application in retrieval. J Document 28:11\u201321. https:\/\/doi.org\/10.1108\/00220410410560573","journal-title":"J Document"},{"key":"9348_CR35","unstructured":"Statista (2020) Global insurance industry\u2013statistics and facts. https:\/\/www.statista.com\/topics\/6529\/global-insurance-industry\/"},{"key":"9348_CR36","unstructured":"SUSEP (2020a) 8\u00b0 Relat\u00f3rio de An\u00e1lise e Acompanhamento dos Mercados Supervisionados. pp 1\u201324. http:\/\/www.susep.gov.br\/menuestatistica\/SES\/relat-acomp-mercado-2020a.pdf"},{"key":"9348_CR37","unstructured":"SUSEP (2020b) Brokers statistics. https:\/\/www2.susep.gov.br\/safe\/Corretores\/estatisticas"},{"key":"9348_CR38","volume-title":"Machine learning: a bayesian and optimization perspective","author":"S Theodoridis","year":"2020","unstructured":"Theodoridis S (2020) Machine learning: a bayesian and optimization perspective, 2nd edn. Elsevier, Amsterdam","edition":"2"}],"container-title":["Artificial Intelligence and Law"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10506-023-09348-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10506-023-09348-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10506-023-09348-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T06:13:05Z","timestamp":1709273585000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10506-023-09348-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,18]]},"references-count":38,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,3]]}},"alternative-id":["9348"],"URL":"https:\/\/doi.org\/10.1007\/s10506-023-09348-9","relation":{},"ISSN":["0924-8463","1572-8382"],"issn-type":[{"value":"0924-8463","type":"print"},{"value":"1572-8382","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,18]]},"assertion":[{"value":"27 January 2023","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 February 2023","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}