Resumen

The main topic of this doctoral dissertation is the extraction of valuable in- formation associated to text documents using di erent graph-based repre- sentations. The core contributions relies on the novel representation of text documents as graphs using lexical and syntactical elements of the language and the employment of this kind of representations, to solve text classi cation tasks or to nd text patterns related to a topic in an innovative way.

The first part (Chapters one to three) of...

Palabras clave: Text mining, graph representations, text classification, topic mining..

Resumen (archivo pdf, 20 kb).

Esta tesis sólo puede ser consultada por miembros de la Comunidad Universitaria. (ir al índice de contenido)

Castillo Juárez, E. 2017. Text Mining Using Graph-Based Representations. Tesis Doctorado. Ciencias de la Computación. Departamento de Computación, Electrónica y Mecatrónica, Escuela de Ingeniería, Universidad de las Américas Puebla. Mayo. Derechos Reservados © 2017.