Diseño De Una Metodología De Análisis De Texto -Una Implementación Desde La Complejidad Y Teoría De Redes Complejas-.

Abstract

The present work consists in developing a methodology for textual analysis applying notions of text mining, complex networks and complexity. The technique proposed in the work aims to provide a tool that allows statistical analysis through Big Data in a text database, which will later be potentially through an R-coded prototype in order to use the advantages that this language provides regarding statistics. The tool used for text mining of selected documents in which cleaning and correction is necessary, due to spelling errors. The updated data will be processed statistically, its complexity will be calculated and displayed through complex networks. Automated analysis will use machine learning techniques, artificial intelligence and data science techniques. With this, the agile treatment of difficult-to-read texts and treatment will be achieved through the hybridization of techniques in a free software environment