Abstract
Pre-trial detention is a debated measure in different legal systems since it deprives defendants of their liberty prior at the initial stage of proceedings. To order this measure, the judge must justify it by highlighting the risks that the arrested person presents to society and to the criminal procedure itself. An example of a factor related to preventive custody, in countries such as Italy and Brazil, is involvement in criminal organizations. The paper presents the results of experimental research with supervised learning, in particular using XAI techniques, such as decision trees and Shapley Additive Explanations. Our corpora are composed of unstructured data (texts of judicial decisions) and structured data (factors extracted from such judicial decisions), from the case law of Italian and Brazilian Supreme Courts. As a result, we have identified a collection of factors that play an important role in the reasoning of the judge and in predicting outcomes, including common factors between the two countries. In particular, we have verified that involvement in criminal organizations consistently leads to the decision to maintain imprisonment in the Brazilian scenario, while in the Italian context, this is unclear. Finally, we conclude that data structuring based on the extraction of factors from the decision texts not only increases the prediction’s quality but also allows for their interpretation and explanation.
This research has been supported by Brazilian National Council for Scientific and Technological Development (CNPq) and Coordination for the Improvement of Higher Education Personnel - Institutional Program for Internationalisation (CAPES/PrInt); ADELE (Analytics for Decision of Legal Cases, EU Justice program Grant (2014–2020); COMPULAW (Computable law), ERC Advanced Grant (2019-2024); LAILA (Legal Analytics for Italian Law), MIUR PRIN Programme (2017), the European Commission under the NextGeneration EU programme, PNRR - M4C2 - Investimento 1.3, Partenariato Esteso PE00000013 - “FAIR - Future Artificial Intelligence Research” - Spoke 8 “Pervasive AI”.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Italian Criminal Code, article 416-bis and Brazilian Law no. 12.850/2013.
- 2.
For all models, the hyperparameters were kept to the default settings from Orange Data Mining.
References
Aggarwal, C.C.: Machine Learning for Text. Springer, Cham (2018)
Aggarwal, C.C., Zhai, C.: A survey of text classification algorithms. In: Aggarwal, C.C., Zhai, C. (eds.) Mining Text Data, pp. 163–222. Springer, New York (2012)
Ashley, K.D.: Prospects for legal analytics: some approaches to extracting more meaning from legal texts. Univ. Cincinnati Law Rev. 90(4), 5 (2022)
Dal Pont, T.R., et al.: Classification and association rules in Brazilian supreme court judgments on pre-trial detention. In: Kö, A., Francesconi, E., Kotsis, G., Tjoa, A.M., Khalil, I. (eds.) EGOVIS 2021. LNCS, vol. 12926, pp. 131–142. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-86611-2_10
Demšar, J., et al.: Orange: data mining toolbox in Python. J. Mach. Learn. Res. 14(1), 2349–2353 (2013)
Dipoppa, G.: How criminal organizations expand to strong states: migrant exploitation and political brokerage in northern Italy (2021)
Došilović, F.K., Brčić, M., Hlupić, N.: Explainable artificial intelligence: a survey. In: 2018 41st International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO), pp. 0210–0215. IEEE (2018)
Hair, J.F., Black, B., Black, W.C., Babin, B.J., Anderson, R.E.: Multivariate Data Analysis. Cengage Learning, Andover (2019)
Horty, J.: Reasoning with dimensions and magnitudes. Artif. Intell. Law 27(3), 309–345 (2019)
Horty, J.F., Bench-Capon, T.J.: A factor-based definition of precedential constraint. Artif. Intell. Law 20(2), 181–214 (2012)
Katz, D.M., Bommarito, M.J., Blackman, J.: A general approach for predicting the behavior of the supreme court of the United States. PLoS ONE 12(4), e0174698 (2017). https://doi.org/10.1371/journal.pone.0174698
Kotu, V., Deshpande, B.: Data Science, 2nd edn. Morgan Kaufmann (Elsevier Science), Cambridge, MA (2019)
Lundberg, S.M., Lee, S.I.: A unified approach to interpreting model predictions. In: Advances in Neural Information Processing Systems, vol. 30 (2017)
Sabo, I.C., Billi, M., Lagioia, F., Sartor, G., Rover, A.J.: Unsupervised factor extraction from pretrial detention decisions by Italian and Brazilian supreme courts. In: Guizzardi, R., Neumayr, B. (eds.) ER 2022. Lecture Notes in Computer Science, vol. 13650, pp. 69–80. Springer, Cham (2023). https://doi.org/10.1007/978-3-031-22036-4_7
Silva, I.N.D., Spatti, D.H., Flauzino, R.A., Liboni, L.H.B., Alves, S.F.D.R.: Artificial Neural Networks. Springer, Switzerland (2018)
Zhang, Y., Haghani, A.: A gradient boosting method to improve travel time prediction. Transp. Res. Part C: Emerg. Technol. 58, 308–324 (2015)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Billi, M., Dal Pont, T.R., Sabo, I.C., Lagioia, F., Sartor, G., Rover, A.J. (2023). Supervised Learning, Explanation and Interpretation from Pretrial Detention Decisions by Italian and Brazilian Supreme Courts. In: Sales, T.P., Araújo, J., Borbinha, J., Guizzardi, G. (eds) Advances in Conceptual Modeling. ER 2023. Lecture Notes in Computer Science, vol 14319. Springer, Cham. https://doi.org/10.1007/978-3-031-47112-4_12
Download citation
DOI: https://doi.org/10.1007/978-3-031-47112-4_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-47111-7
Online ISBN: 978-3-031-47112-4
eBook Packages: Computer ScienceComputer Science (R0)