Detección intrínseca de plagio

[EN] In this thesis we focus on the intrinsic plagiarism detection by means of the application of diverse stylistic traditional measures and of two new measures proposed that we are called Index of Local Concorcande or ICL and, his generalization, General Index of Local Concordance or IGCL. In order...

Descripción completa

Detalles Bibliográficos
Autor: Pérez Afonso, Javier
Tipo de recurso: tesis de maestría
Fecha de publicación:2013
País:España
Institución:Universitat Politècnica de València (UPV)
Repositorio:RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Idioma:español
OAI Identifier:oai:riunet.upv.es:10251/43831
Acceso en línea:https://riunet.upv.es/handle/10251/43831
Access Level:acceso abierto
Palabra clave:Detección de plagio
Medidas estílísticas
Agrupación de documentos
Plagiarism detection
Stylistic measures
Documentos clusters
LENGUAJES Y SISTEMAS INFORMATICOS
Máster Universitario en Inteligencia Artificial, Reconocimiento de Formas e Imagen Digital-Màster Universitari en Intel·ligència Artificial, Reconeixement de Formes i Imatge Digital
Descripción
Sumario:[EN] In this thesis we focus on the intrinsic plagiarism detection by means of the application of diverse stylistic traditional measures and of two new measures proposed that we are called Index of Local Concorcande or ICL and, his generalization, General Index of Local Concordance or IGCL. In order to do realize the detection we propose two methods that use a set of stylistic measures. The first method is learn of the set example of documents the relevant characteristics, to be able to separate in plagiarism documents and no plagiarism documents. The second one, allows to recognize the documents fragments that not preserve the style of the majority of the document and therefore might be considered as plagiarism fragments.