• JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
 
  Bookmark and Share
 
 
Master's Dissertation
DOI
https://doi.org/10.11606/D.59.2020.tde-04012021-232455
Document
Author
Full name
Vithor Gomes Ferreira Bertalan
E-mail
Institute/School/College
Knowledge Area
Date of Defense
Published
Ribeirão Preto, 2020
Supervisor
Committee
Ruiz, Evandro Eduardo Seron (President)
Baranauskas, José Augusto
Oliveira, Cristina Godoy Bernardo de
Quaresma, Paulo
Title in English
Using natural language processing methods to predict judicial outcomes
Keywords in English
Legal classifier
Legal prediction
Natural language processing
Abstract in English
Natural Language Processing (NLP) and Artificial Intelligence (AI) for the field of Law is a growing area, with the potential of radically changing the daily routine of legal professionals. The amount of text generated by those professionals is outstanding, and to this point, it is a knowledge area to be more explored by Computer Science. One of the most acclaimed fields for the combined area of NLP, AI, and Law is Legal Prediction, in which intelligent systems try to predict specific judicial characteristics, such as the judicial outcome or the judicial class or a given case. This research creates classifiers to predict judicial outcomes in the Brazilian legal system. For this purpose, we developed a text crawler to extract data from the official Brazilian electronic legal systems. Afterward, we developed a dataset of Second Degree Murder and Active Corruption cases, and different classifiers, such as Support Vector Machines and Neural Networks, were used to predict judicial outcomes by analyzing textual features. As a final goal, we used the findings of one of the algorithms, Hierarchical Attention Networks, to find a sample of the most important words used to absolve or convict defendants.
Title in Portuguese
Usando métodos de processamento de linguagem natural para prever resultados judiciais
Keywords in Portuguese
Classificador jurídico
Predição jurídica
Processamento de linguagem natural
Abstract in Portuguese
Processamento de Linguagem Natural (PLN) e Inteligência Artificial (IA) para a Área Jurídica é uma área em crescimento, com o potencial de mudar radicalmente a rotina diária dos profissionais jurídicos. A quantidade de texto gerada por estes profissionais é imensa, e até o momento inexplorada pela Ciência da Computação. Uma das áreas mais aclamadas é a Predição Jurídica, onde sistemas inteligentes tentam predizer certas características jurídicas, como os pareceres ou a classe jurídica de um dado caso. Esta pesquisa cria classificadores para predizer pareceres jurídicos no sistema legal brasileiro. Para atingir este objetivo, desenvolvemos um rastreador de texto para retirar dados dos sistemas eletrônicos legais do Brasil. Depois, criamos um conjunto de dados composto por casos de Homicídio Simples e Corrupção Ativa, e diferentes classificadores, como máquinas de vetores suporte e redes neurais, foram utilizados com o objetivo de predizer os pareceres através da observação das características textuais. Como um objetivo final, utilizamos os resultados de um dos algoritmos, as Hierarchical Attention Networks, para achar exemplos das palavras que foram mais importantes para absolver ou condenar réus.
 
WARNING - Viewing this document is conditioned on your acceptance of the following terms of use:
This document is only for private use for research and teaching activities. Reproduction for commercial use is forbidden. This rights cover the whole data about this document as well as its contents. Any uses or copies of this document in whole or in part must include the author's name.
Publishing Date
2021-01-22
 
WARNING: Learn what derived works are clicking here.
All rights of the thesis/dissertation are from the authors
CeTI-SC/STI
Digital Library of Theses and Dissertations of USP. Copyright © 2001-2024. All rights reserved.