Preventing Spam Blogs Using Content Analysis and User Behaviour Model

Spam blog is a subset of blog which contains nothing more than stolen materials and inauthentic text designed to gain profit from various type of advertisements. Splogs have become a nuisance in the blogosphere because it pollutes search engine results and blog update servers. This paper discusses t...

Description complète

Détails bibliographiques
Auteur principal: Mohammad Hafiz, Ismail
Format: Thèse
Langue:anglais
anglais
Publié: 2007
Sujets:
Accès en ligne:https://etd.uum.edu.my/21/1/mohammad_hafiz.pdf
https://etd.uum.edu.my/21/2/mohammad_hafiz.pdf
Description
Résumé:Spam blog is a subset of blog which contains nothing more than stolen materials and inauthentic text designed to gain profit from various type of advertisements. Splogs have become a nuisance in the blogosphere because it pollutes search engine results and blog update servers. This paper discusses the similarity between spam blogs and email spams and the techniques used to identify them. The paper also propose the development of a prototype blog update server that implements content analysis and user behaviour model to filter splogs before they are indexed into blog search engine.