Publication Details

Text-Based Web Page Classification with Use of Visual Information

BARTÍK Vladimír. Text-Based Web Page Classification with Use of Visual Information. In: 2010 International Conference on Advances in Social Network Analysis and Mining. Odense: IEEE Computer Society, 2010, pp. 416-420. ISBN 978-0-7695-4138-9.
Czech title
Klasifikace webových stránek založená na textu s využitím vizuální informace
Type
conference paper
Language
english
Authors
Bartík Vladimír, Ing., Ph.D. (DIFS FIT BUT)
Keywords

web page classification, term weights, text classification, TF-IDF weight, visual information, visual  blocks

Abstract

As the number of pages on the web is permanently increasing, there is a need to classify pages into categories to facilitate indexing or searching them. In the method proposed here, we use both textual and visual information to find a suitable representation of web page content. In this paper, several term weights, based on TF or TF-IDF weighting are proposed. Modification is based on visual areas, in which the text appears and their visual properties. Some results of experiments are included in the final part of the paper.

Published
2010
Pages
416-420
Proceedings
2010 International Conference on Advances in Social Network Analysis and Mining
Conference
International Symposium on Open Source Intelligence & Web Mining 2010, Odense, DK
ISBN
978-0-7695-4138-9
Publisher
IEEE Computer Society
Place
Odense, DK
BibTeX 
@INPROCEEDINGS{FITPUB9274,
   author = "Vladim\'{i}r Bart\'{i}k",
   title = "Text-Based Web Page Classification with Use of Visual Information",
   pages = "416--420",
   booktitle = "2010 International Conference on Advances in Social Network Analysis and Mining",
   year = 2010,
   location = "Odense, DK",
   publisher = "IEEE Computer Society",
   ISBN = "978-0-7695-4138-9",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/9274"
}
Back to top