Panel s nápovědou

Text Representation and Its Influence on Text Categorization

Created at the Faculty of Information Technology, BUT, Brno
Authors: Ondřej Šabatka, Vladimír Bartík
Kontakt: xsabat05@stud.fit.vutbr.cz, bartik@fit.vutbr.cz

This program enables text preprocessing of documents for text mining It offers several possibilities of document representation and several pre-processing methods. There is also a possibility of using N-Grams as features for document representation.

More information about setting the pre-processing options and various functions of the program will be displayed in this help panel.

Components of the program

This program consists of the following four componenets
  1. Reading of text documents
  2. Setting of text document pre-processing options
  3. Displaying information about the pre-processed dataset
  4. Possibility to store the representation into a file for further use.