Author(s)

C. A. S. A. do Nascimento, N. F. F. Ebecken & J. L. dos A. Rosa

Abstract

This paper has the objective of developing a methodology to store a great mass of semi-structured data and its later recovery, focusing on possible improvements and applications by text mining, uniting related articles from many specialties. The present work intends to contribute by way of supplying a strong methodology based on text mining algorithms, searching for a better automated analysis of documents by text classification and making it easy to store and acquire the relevant information in documents on the Web. Keywords: data mining, text mining, KNN classification.

Keywords

data mining, text mining, KNN classification.