• 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.100.2020.tde-04112020-152132
Document
Author
Full name
Caio Deutsch
E-mail
Institute/School/College
Knowledge Area
Date of Defense
Published
São Paulo, 2020
Supervisor
Committee
Paraboni, Ivandré (President)
Carvalho, Ariadne Maria Brito Rizzoni
Pérez-Alcazár, José de Jesus
Title in Portuguese
Atribuição autoral com uso de classificadores de perfis
Keywords in Portuguese
Aprendizado de máquinas
Atribuição autoral
Caracterização autoral
Distorções textuais
Processamento de língua natural
Abstract in Portuguese
A atribuição autoral (AA) busca identificar um autor de texto a partir de um conjunto de autores conhecidos. Autores deixam rastros em seus textos e é possível identificar características sociolinguísticas baseadas no estilos de escrita refletidos no texto destes autores. A atribuição autoral está cada vez mais demonstrando importância para diversas atividades sociais, em especial para a análise forense. Os trabalhos envolvendo AA demonstram resultados modestos e motivam a exploração de diferentes técnicas para melhorar a acurácia dos modelos atuais. A partir desses pontos, o presente trabalho apresenta uma proposta de pesquisa em nível de mestrado no campo de processamento de língua natural (PLN), com ênfase em AA, com o objetivo geral de melhorar o desempenho de classificadores de atribuição autoral utilizando técnicas de caracterização autoral (CA)
Title in English
Author attribution using profile classifiers
Keywords in English
Author attribution
Author characterization
Machine learning
Natural language processing
Textual distortions
Abstract in English
Author attribution (AA) seeks to identify a text author from a set of known authors. Authors leave traces in their texts and it is possible to identify sociolinguistic characteristics based on the writing styles reflected in the text of these authors. Author attribution is increasingly showing importance for various social activities, especially forensic analysis. Studies involving AA show modest results and motivate the exploration of different techniques to improve the accuracy of current models. From these perspective, this project presents a master's level research proposal in the field of natural language processing (NLP), with an emphasis in AA, with the general objective of improving the performance of AA classifiers using author profiling techniques
 
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
2021-07-06
 
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.