The text document processing in the information retrieval from web pages

Abstract EN

The paper describes possible representation models and ways of weighting text documents, which can be found on the Internet.

The focus is on automatic extraction of information from texts including pre-processing of text documents.

The paper presents also results of experiments, which were carried out using the 20 News Groups collection of documents.

These experiments concern with the influence of the training set cardinality and a suitable weighting of text documents to the precision of document classification.

The results of experiments with k-means clustering and k-means clustering with controlled initialization are also presented.