CLASSIFICATION DES PAGES WEB BASEES SUR UNE TECHNIQUE D’EXTRACTION DES MOTS CLES
No Thumbnail Available
Date
2021
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Wit h the increase in the number of Internet users, the growth of websites is proportional. As a
result, the ranking of web pages has become a huge topic of research in recent years. This has
made an ever-increasing demand for automated classification techniques wit h high
classification accuracy. To automat ically categorize and manipulate web pages, current
systems use visual page content, which includes displayed content. However, so far, litt le
work has been done on the use of textual content and HTML code.
In this work, we propose a method of classification of Web pages, based on their textual
content. Web pages generally present informat ion of various different classes depending on
their specific subject matter. This method is based on the technique of extracting keywords
from a web page (textual content) combined wit h a supervised approach to machine learning,
namely neural networks.
Keywords: web page classificat ion, keyword extraction, supervised approaches, machine
learning