Análise do âmbito da integração da inteligência artificial e da aprendizagem automática com instrumentos estruturados para prever a reincidência juvenil

Autores

DOI:

https://doi.org/10.46661/respublica.13244

Palavras-chave:

Inteligência artificial, aprendizagem automática, avaliação de riscos, reincidência juvenil, justiça juvenil

Resumo

A previsão do risco de reincidência na justiça juvenil tem-se baseado tradicionalmente em instrumentos estruturados, enquanto a incorporação de modelos de IA/ML tem sido proposta como uma forma de melhorar o seu desempenho. No entanto, o valor acrescentado real destes modelos, a sua integração com ferramentas estruturadas e as suas implicações para a prática continuam a ser objeto de debate. A presente revisão de alcance sintetiza a evidência empírica disponível sobre a aplicação de IA/ML na população juvenil quando existe uma ligação com instrumentos estruturados de avaliação de risco. Foram incluídos cinco estudos que cumpriam estes critérios. Em conjunto, os resultados mostram um padrão consistente de discriminação moderada e melhorias geralmente marginais ao aumentar a complexidade dos modelos, o que sugere a existência de um certo limite empírico na capacidade preditiva neste domínio. As melhorias são mais prováveis quando o comparador é estritamente linear ou quando se contrasta com o julgamento não estruturado, o que aponta para que o valor acrescentado da IA/ML pode consistir em modelar as interações entre variáveis, em vez de um aumento substancial da precisão. No entanto, o desempenho agregado pode ocultar diferenças relevantes entre subgrupos, incluindo as disparidades associadas a variáveis sociodemográficas, o que tem implicações em termos de equidade e legitimidade institucional. A isto acrescentam-se os desafios decorrentes da sua implementação, incluindo a rastreabilidade dos modelos, a interação entre profissionais e sistemas automatizados e a necessidade de quadros normativos que garantam a supervisão e a revisão.

Downloads

Não há dados estatísticos.

Referências

ARGUDO Aaron., MANEIRO, Lorena., & GÓMEZ-FRAGUELA, Xose Anton. (2021). Protocolo de valoración del riesgo en un adolescente en libertad vigilada. REC: Revista Electrónica de Criminología, 4, 1-6.

ARKSEY, Hilary., & O’Malley, Lisa. (2005). Scoping studies: towards a methodological framework. International Journal of Social Research Methodology, 8(1), 19–32. https://doi.org/10.1080/1364557032000119616

BARNOSKI, Robert. (2004). Washington State Juvenile Court Assessment Manual (Version 2.1). Olympia, WA: Washington State Institute for Public Policy. https://doi.org/10.1037/t04488-000

BERK, Richard. A. (2021). Artificial intelligence, predictive policing, and risk assessment for law enforcement. Annual Review of Criminology, 4(1), 209–237. https://doi.org/10.1146/annurev-criminol-051520-012342

BERRÍOS DÍAZ, Gonzalo. (2022). Individualización de las medidas de sanción en la persona adolescente. En Manual de justicia penal para adolescentes (pp. 417–456).

BONTA, James., & ANDREWS, Donlad. A. (2007). Risk-need-responsivity model for offender assessment and rehabilitation. Department of Public Safety and Emergency Preparedness Canada. https://doi.org/10.4324/9781003292128

BONTA, J., & ANDREWS, Donald. A. (2023). The psychology of criminal conduct (7a ed.). Routledge. https://doi.org/10.4324/9781003292128

BORUM, Randy., BARTEL, Patrick., & FORTH, Adelle. (2006). Manual for the Structured Assessment of Violence Risk in Youth (SAVRY). Odessa, FL: Psychological Assessment Resources.

CHOULDECHOVA, Alexandra. (2017). Fair prediction with disparate impact: A study of bias in recidivism prediction instruments. Big Data, 5(2), 153–163. https://doi.org/10.1089/big.2016.0047 PMid:28632438

COLLIOT, Olivier. (2023). A non-technical introduction to machine learning. En Machine Learning for Brain Disorders (pp. 3–23). Springer US. https://doi.org/10.1007/978-1-0716-3195-9 PMid:37988480

CUEVAS, Carlos., WOLFF, Kevin. T., & BAGLIVIO, Michael T. (2019). Dynamic risk factors and timing of recidivism for youth in residential placement. Journal of Criminal Justice, 60, 154–166. https://doi.org/10.1016/j.jcrimjus.2018.10.003

Eaglin, Jessica. (2016). Constructing recidivism risk for sentencing. SSRN Electronic Journal. https://doi.org/10.2139/ssrn.2821136

ENGEL, Christoph., & GRGIĆ-HLAČA, Nina. (2021). Machine advice with a warning about machine limitations: Experimentally testing the solution mandated by the Wisconsin Supreme Court. The Journal of Legal Analysis, 13(1), 284–340. https://doi.org/10.1093/jla/laab001

FERNÁNDEZ-MOLINA, Esther., & BARTOLOMÉ, Raquel. (2020). Delincuencia y justicia juvenil en España: ¿qué sabemos?. Tirant lo Blanch.

FLORIDA DEPARTMENT OF JUVENILE JUSTICE. (s.f.). Prevention Assessment Tool (PAT): User Manual. Tallahassee, FL: Office of Prevention Services.

GARRIDO, Vicente., LÓPEZ, Enrique., & GALVIS, Domenech. (2017). Predicción de la reincidencia con delincuentes juveniles: adaptación del IGI-J. Revista sobre la infancia y la adolescencia, 12, 30. https://doi.org/10.4995/reinad.2017.6484

GHASEMI, Mehdi., ANVARI, Daniel., ATAPOUR, Mahshid., STEPHEN WORMITH, J., STOCKDALE, Keira. C., & SPITERI, R. J. (2021). The application of machine learning to a general risk–need assessment instrument in the prediction of criminal recidivism. Criminal Justice and Behavior, 48(4), 518–538. https://doi.org/10.1177/0093854820969753

GÓMEZ-FRAGUELA, Xose. Anton., CUTRÍN, Olalla., & MANEIRO, Lorena & LUENGO- MARTIN Angeles. (2019). Valoración del riesgo en adolescentes infractores (VRAI). Andavira

GÓMEZ-FRAGUELA, Jose Antonio., MANEIRO, Lorena., CUTRÍN, Olalla., & ARGUDO, Aaron. (2021). Tratado sobre delincuencia juvenil y responsabilidad penal del menor: a los 20 años de la Ley Orgánica 5-2000, de 12 de enero, reguladora de la responsabilidad penal de los menores (E. A. Abadías, Ed.). Wolters Kluwer.

GREENE, Travis., SHMUELI, Galit., FELL, Jan., LIN, Ching-Fu., & LIU, Han-Wei. (2022). Forks over knives: Predictive inconsistency in criminal justice algorithmic risk assessment tools. Journal of the Royal Statistical Society: Series A (Statistics in Society), 185(Suppl_2), S692–S723. https://doi.org/10.1111/rssa.12966

HELMUS, Leslie. Maaike., & BABCHISHIN, Kelly. (2017). Primer on risk assessment and the statistics used to evaluate its accuracy. Criminal Justice and Behavior, 44(1), 8–25. https://doi.org/10.1177/0093854816678898

HILTERMAN, Ed. L. B., VERMUNT, Jeroen. K., NICHOLLS, Tonia. L., BONGERS, Ilja. L., & NIEUWENHUIZEN, Chris van. (2019). Profiles of SAVRY risk and protective factors within male and female juvenile offenders: A latent class and latent transition analysis. International Journal of Forensic Mental Health, 18(4), 350–364. https://doi.org/10.1080/14999013.2019.1580803

HOFFMAN, Peter. B., & BECK, James., L. (1974). Parole decision-making: A salient factor score. Journal of Criminal Justice, 2(3), 195–206. https://doi.org/10.1016/0047-2352(74)90031-2

HOGE, R. D. Y ANDREWS, D. A. (2002). Youth Level of Service/Case Management Inventory (YLS/CMI) User’s manual. Multi-Health Systems.

HOGE, R. D., & ANDREWS, D. A. (2011). Youth Level of Service/Case Management Inventory 2.0 (YLS/CMI 2.0): User’s manual. Multi-Health Systems. https://doi.org/10.1037/t05078-000

JAMES, Gareth., WITTEN, Daniela., HASTIE, Trevor., & TIBSHIRANI, Robert. (2021). An introduction to statistical learning: With applications in R (2a ed.). Springer. https://doi.org/10.32614/CRAN.package.ISLR2

KIGERL, Alex., HAMILTON, Zachary., KOWALSKI, Melissa., & MEI, Xiaohan. (2022). The great methods bake-off: Comparing performance of machine learning algorithms. Journal of Criminal Justice, 82(101946), 101946. https://doi.org/10.1016/j.jcrimjus.2022.101946

LEY DE 12 DE AGOSTO DE 1904 SOBRE PROTECCIÓN A LA INFANCIA. (17 de agosto de 1904). Gaceta de Madrid, (230), 589–590. https://www.boe.es/buscar/doc.php?id=BOE-A-1904-5148

LEY DE 2 DE AGOSTO DE 1918 AUTORIZANDO AL GOBIERNO PARA PUBLICAR UNA LEY SOBRE ORGANIZACIÓN Y ATRIBUCIONES DE LOS TRIBUNALES PARA NIÑOS. (15 de agosto de 1918). Gaceta de Madrid, (227), 470. https://www.boe.es/gazeta/dias/1918/08/15/pdfs/GMD-1918-227.pdf

LEY ORGÁNICA 5/2000, DE 12 DE ENERO, REGULADORA DE LA RESPONSABILIDAD PENAL DE LOS MENORES. (13 de enero de 2000). Boletín Oficial del Estado, (11), 1422–1441. https://www.boe.es/eli/es/lo/2000/01/12/5

LOINAZ, Ismael. (2017). Manual de evaluación del riesgo de violencia: metodología y ámbitos de aplicación. Pirámide.

MINISTRY OF JUSTICE. (s.f.). Case Assessment Tool for Juvenile Offenders (MJCA). Tokyo, Japan: Rehabilitation Bureau, Ministry of Justice.

MIRON, Marius., TOLAN, Songul., GÓMEZ, Emilia., & CASTILLO, Carlos. (2021). Evaluating causes of algorithmic bias in juvenile criminal recidivism. Artificial Intelligence and Law, 29(2), 111–147. https://doi.org/10.1007/s10506-020-09268-y

MONAHAN, John., & SKEEM, Jennifer. L. (2016). Risk assessment in criminal sentencing. Annual Review of Clinical Psychology, 12(1), 489–513. https://doi.org/10.1146/annurev-clinpsy-021815-092945 PMid:26666966

MOONS, Karel. G. M., WOLFF, Robert. F., RILEY, Richard. D., WHITING, Penny. F., WESTWOOD, Marie., COLLINS, Gary. S., REITSMA, Jihannes. B., KLEIJNEN, Jis., & MALLETT, Sue. (2019). PROBAST: A tool to assess risk of bias and applicability of prediction model studies: Explanation and elaboration. Annals of Internal Medicine, 170(1), W1–W33. https://doi.org/10.7326/M18-1377 PMid:30596876

MORI, Takemi., HARADA, Kyoko., YAMAKI, Mayuko., & YAMAGUCHI, Masatoshi. (2024). The limited value of machine learning approach to improving predictive performance: The Ministry of Justice Case Assessment Tool. Psychology, Public Policy, and Law: An Official Law Review of the University of Arizona College of Law and the University of Miami School of Law, 30(2), 171–178. https://doi.org/10.1037/law0000421

PETERS, Micah., GODFREY, Christina., MCINERNEY, Patricia., MUNN, Zachary., TRICO, Andrea., & KHALIL, Hanan. (2020). Chapter 11: Scoping reviews. En JBI Manual for Evidence Synthesis. JBI. https://doi.org/10.46658/JBIRM-20-01

RAICHE, Ann- Pierre., DAUPHINAIS, Leanne., DUVAL, Manon., DE LUCA, Gino., RIVEST-HÉNAULT, David., VAUGHAN, Thomas., PROULX, C., & GUAY, Jean-Pierre. (2023). Factors influencing acceptance and trust of chatbots in juvenile offenders’ risk assessment training. Frontiers in Psychology, 14, 1184016. https://doi.org/10.3389/fpsyg.2023.1184016 PMid:37397322 PMCid:PMC10312240

SHEPPARD, Keller. G., TALAUGON, Alyssa. R., & HERNANDEZ, Jorge. L. (2024). Assessing the feasibility and performance of risk assessment instruments for early intervention and prevention services in Juvenile Justice. Journal of Criminal Justice, 94(102262), 102262. https://doi.org/10.1016/j.jcrimjus.2024.102262

STEVENSON, Megan. T., & DOLEAC, Jennifer. L. (2024). Algorithmic risk assessment in the hands of humans. American Economic Journal. Economic Policy, 16(4), 382–414. https://doi.org/10.1257/pol.20220620

STEYERBERG, Ewout. W. (2019). Clinical prediction models: A practical approach to development, validation, and updating. Springer International Publishing. https://doi.org/10.1007/978-3-030-16399-0

TASHARROFI, Shahin., & BARNES, J. C. (2022). Optimizing community supervision practices with the Elo-rating system: A proof-of-concept. Justice Evaluation Journal, 5(2), 288–306. https://doi.org/10.1080/24751979.2022.2052343

TAXMAN, Faye. S., & SMITH, Lindsay. (2021). Risk-Need-Responsivity (RNR) classification models: Still evolving. Aggression and Violent Behavior, 59(101459), 101459. https://doi.org/10.1016/j.avb.2020.101459

THOMPSON, Kristen. C., & MORRIS, Richard. J. (2016). History of the juvenile justice system. En Advancing Responsible Adolescent Development (pp. 55–72). Springer International Publishing. https://doi.org/10.1007/978-3-319-29343-1_5

TING, Ming. Hwa., CHU, Chi. Meng., ZENG, Gerald., LI, Dongdong., & CHNG, Grace. S. (2018). Predicting recidivism among youth offenders: Augmenting professional judgement with machine learning algorithms. Journal of Social Work (London, England), 18(6), 631–649. https://doi.org/10.1177/1468017317743137 PMid:30473627 PMCid:PMC6210571

TRAVAINI, Guido. Vittorio., PACCHIONI, Federico., BELLUMORE, Silvia., BOSIA, Marta., & DE MICCO, Francesco. (2022). Machine learning and criminal justice: A systematic review of advanced methodology for recidivism risk prediction. International Journal of Environmental Research and Public Health, 19(17), 10594. https://doi.org/10.3390/ijerph191710594 PMid:36078307 PMCid:PMC9517748

TRICCO, Andrea. C., LILLIE, Erin., ZARIN, Wasifa., O’BRIEN, Kelly. K., COLQUHOUN, Heather., LEVAC, Danielle., MOHER, David., PETERS, Micah. D. J., Horsley, Tanya., Weeks, Laura., HEMPEL, Susanne., AKL, Elie. A., CHANG, Christine., MCGOWAN, Jessie.,STEWART, Lewin., HARTLING, Lisa., Aldcroft, Adrian., Wilson, Micheal. G., GARRITTY, C., … STRAUS, Sharon. E. (2018). PRISMA extension for Scoping Reviews (PRISMA-ScR): Checklist and explanation. Annals of Internal Medicine, 169(7), 467–473. https://doi.org/10.7326/M18-0850 PMid:30178033

UGWUDIKE, Pamela. (2022). Predictive algorithms in justice systems and the limits of tech-reformism. International Journal for Crime Justice and Social Democracy, 11(1), 85–99. https://doi.org/10.5204/ijcjsd.2189

VERREY, Jacob., NEYROUD, Peter., SHERMAN, Lawrence., & ARIEL, Barak. (2025). A fairness scale for real-time recidivism forecasts using a national database of convicted offenders. Neural Computing & Applications, 37(26), 21607–21657. https://doi.org/10.1007/s00521-025-11478-x PMid:40904695 PMCid:PMC12401775

WANG, Caroline., HAN, Bin., PATEL, Bhrij., & RUDIN, Cynthia. (2023). In pursuit of interpretable, fair and accurate machine learning for criminal recidivism prediction. Journal of Quantitative Criminology, 39(2), 519–581. https://doi.org/10.1007/s10940-022-09545-w

WOLFF, Robert. F., MOONS, Karel. G. M., RILEY, Richard. D., WHITING, Penny. F., WESTWOOD, Marie., COLLINS, Gary. S., REITSMA, Johannes. B., KLEIJNEN, Jos., MALLETT, Sue., & PROBAST GROUP†. (2019). PROBAST: A tool to assess the risk of bias and applicability of prediction model studies. Annals of Internal Medicine, 170(1), 51–58. https://doi.org/10.7326/M18-1376 PMid:30596875

WORMITH, J. Stephan., & ZIDENBERG, Alexandra. M. (2018). The historical roots, current status, and future applications of the risk-need-responsivity model (RNR). En New Frontiers in Offender Treatment (pp. 11–41). Springer International Publishing. https://doi.org/10.1007/978-3-030-01030-0_2

YUKHNENKO, Denis., BLACKWOOD, Nigel, LICHTENSTEIN, Paul., & FAZEL, Seena. (2025). Dynamic prediction of reoffending in individuals given community sentences: Development and validation of a novel risk monitoring assessment tool (oxMore). Law and Human Behavior. https://doi.org/10.1037/lhb0000641 PMid:41343387 PMCid:PMC7618717

ZAVRŠNIK, Ales. (2020). Criminal justice, artificial intelligence systems, and human rights. ERA Forum, 567–583. https://doi.org/10.1007/s12027-020-00602-0

Downloads

Publicado

2026-05-25

Como Citar

Argudo Palacios, Aarón, e Amal Mechraoui. 2026. «Análise Do âmbito Da integração Da Inteligência Artificial E Da Aprendizagem automática Com Instrumentos Estruturados Para Prever a Reincidência Juvenil». RES PUBLICA Cadernos De Direito E Criminologia, maio, 1-16. https://doi.org/10.46661/respublica.13244.

Edição

Secção

Artículos

Artigos Similares

1 2 3 4 > >> 

Também poderá iniciar uma pesquisa avançada de similaridade para este artigo.