• 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.104.2024.tde-03042024-080044
Document
Author
Full name
Robson Ortz Oliveira Cunha
Institute/School/College
Knowledge Area
Date of Defense
Published
São Carlos, 2024
Supervisor
Committee
Stern, Rafael Bassi (President)
Esteves, Luís Gustavo
Prates, Marcos Oliveira
Title in Portuguese
Modelo Hierárquico Bayesiano Não Paramétrico Aplicado em Modelagem de Tópicos
Keywords in Portuguese
Jurimetria
Modelagem de tópicos textuais
Modelo não paramétrico Bayesiano
Processo hierárquico de Dirichlet
Abstract in Portuguese
Dada a crescente necessidade e importância da análise de dados textuais no ramo da inteligência artificial, modelos que possam compreender melhor a linguagem humana e lidar com dados não estruturados têm ganhado cada vez mais relevância. Neste trabalho, desenvolvemos um estudo sobre o Processo Hierárquico de Dirichlet (HDP) na modelagem de tópicos textuais explorando seus aspectos práticos ao aplicá-lo em um conjunto de dados (corpus) de processos jurídicos, compostos por três tipos de procedimentos distintos. Discorremos sobre as principais propriedades do HDP, sobre a ótica Bayesiana, assumindo que os dados sejam oriundos de uma distribuição de probabilidade Multinomial, baseados no modelo de representação textual de bag-of-words, comumente utilizado em processamento de linguagem natural. Procedemos ainda com algumas técnicas de pré-processamento textual, que resultaram em documentos (dados) mais parcimoniosos, e com estudo de simulação para verificar a performance do modelo. Ao fim do trabalho, apresentamos os resultados das aplicações realizadas e discutimos sobre a problemática da análise de dados em jurimetria.
Title in English
Nonparametric Bayesian Hierarchical Model Applied to Topic Modeling
Keywords in English
Hierarchical Dirichlet process
Jurimetry
Non-parametric Bayesian model
Topic modeling
Abstract in English
Given the growing need and importance of analyzing textual data in the field of artificial intelligence, models that can better understand human language and deal with unstructured data are increasingly relevant gains. In this work, we developed a study on the Hierarchical Dirichlet Process (HDP) in modeling textual topics, exploring its practical aspects by applying it to a data set (corpus) of legal process, composed of three types of different procedures. We will discuss the main properties of HDP, from a Bayesian perspctive, assuming that the data comes from Multinomial probability distribution, based on the bag-of-words textual representation model, commonly used in natural language processing. We also proceeded with some textual pre-processing techniches, which resulted in more parsimonious documents (data), and with a simulation study to verify the model's performance. At the end of the work, we present the results of the applications carried out and discuss the issues of data analysis in jurimetry.
 
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
2024-04-03
 
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.