The 7-Phases Preprocessing Based On Extractive Text Summarization

Extractive text summarization is an approach to automatic text summarization whose main purpose is to reduce the size of the document while preserving the information of the original document. In this study, 7-phase preprocessing is proposed as a preprocessing composition to clean text data so that it is ready to enter data into the summary method such as machine learning. The composition of 7-phase preprocessing is data frame by sentence, remove title from data frame, lower caseing, remove punctuations, remove stop words, tokenizing and stemming. The preprocessing model was tested on the DUC 2002 dataset which is a news document. The performance of the proposed preprocessing stage for extractive summarization showed superior results compared to the combination of other comparison preprocessing stages with ROUGE-1 measurements (recall, precision, and F-1).