Enhancing web page classification through image-block importance analysis

We present a term weighting approach for improving web page classification, based on the assumption that the images of a web page are those elements which mainly attract the attention of the user. This assumption implies that the text contained in the visual block in which an image is located, calle...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Information processing & management Jg. 44; H. 4; S. 1431 - 1447
Hauptverfasser: Fersini, E., Messina, E., Archetti, F.
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Kidlington Elsevier Ltd 01.07.2008
Elsevier
Elsevier Science Ltd
Schlagworte:
Algorithms
Classification
Content analysis
Document classification
Exact sciences and technology
Indexing. Classification. Abstracting
Indexing. Classification. Abstracting. Syntheses
Information and communication sciences
Information and document structure and analysis
Information processing and retrieval
Information retrieval
Information retrieval. Man machine relationship
Information science. Documentation
Internet
Layout
Research process. Evaluation
Sciences and techniques of general use
Studies
Term weighting
Vector space model
Visual layout analysis
Web pages
Websites
Weighting
Vector space model
Visual layout analysis
Document classification
Term weighting
Image analysis
Automatic classification
Vector space
Bayes method
Web mining
Information extraction
Information retrieval system
ISSN:0306-4573, 1873-5371
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:We present a term weighting approach for improving web page classification, based on the assumption that the images of a web page are those elements which mainly attract the attention of the user. This assumption implies that the text contained in the visual block in which an image is located, called image-block, should contain significant information about the page contents. In this paper we propose a new metric, called the Inverse Term Importance Metric, aimed at assigning higher weights to important terms contained into important image-blocks identified by performing a visual layout analysis. We propose different methods to estimate the visual image-blocks importance, to smooth the term weight according to the importance of the blocks in which the term is located. The traditional TFxIDF model is modified accordingly and used in the classification task. The effectiveness of this new metric and the proposed block evaluation methods have been validated using different classification algorithms.
Bibliographie:SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
ObjectType-Article-1
ObjectType-Feature-2
content type line 23
ISSN:0306-4573
1873-5371
DOI:10.1016/j.ipm.2007.11.003