ANALYSIS OF THE IMPACT OF TEXT PREPROCCESSING ON THE RESULTS OF TEXT CLASSIFICATION

The main approaches of text preprocessing were investigated. The effect of text preprocessing on the classification results was investigated. On the basis of a range of documents, classification was performed with and without usage of text preprocessing. The accuracy metrics of the classifier and the time spent on processing documents were reviewed. Based on the results, conclusions were drawn on the relevance of the use of text processing in terms of text classification.