WebGuard: Web based adult content detection and filtering system

Author

Hammami, Mohamed ; CHAHIR, Youssef ; Chen, Liming

Author_Institution

Ecole Centrale de Lyon, Ecully, France

fYear

2003

fDate

13-17 Oct. 2003

Firstpage

574

Lastpage

578

Abstract

We describe a Web filtering system "WebGuard", which aims to automatically detect and filter adult content on the Web. WebGuard uses Web crawler to extract relevant data from the Web, combines the textual content, the image content, and the URL name of a Web page to construct its feature vector. WebGuard uses data mining techniques to classify URLs into two classes: suspect URLs and normal URLs. The suspect URLs are stored in a database, which is constantly and automatically updated in order to reflect the highly dynamic evolution of the Web. When working, WebGuard simply captures a user\´s URL, matches it with the suspect URLs stored in the database and takes an appropriate action - filtering or blocking - according to the result of the analysis. Our preliminary results show that it can detect and filter adult content effectively.

Keywords

Internet; client-server systems; data mining; information filters; information retrieval; URL name; Web crawler; Web page; WebGuard filtering system; adult content detection; client-server architecture; data extraction; data mining techniques; image content; normal URL; suspect URL; textual content; Crawlers; Data mining; Image databases; Information analysis; Information filtering; Information filters; Internet; Spatial databases; Uniform resource locators; Web pages;

fLanguage

English

Publisher

ieee

Conference_Titel

Web Intelligence, 2003. WI 2003. Proceedings. IEEE/WIC International Conference on

Print_ISBN

0-7695-1932-6

Type

conf

DOI

10.1109/WI.2003.1241271

Filename

1241271