Comprehensive analysis of web page classifier for Fsocused crawler

Abstract

Focused Crawler collects domain specific web page from the internet. However, the performance of focused web crawler depends upon the multidimensional nature of the web page. This paper presents a comprehensive analysis of recent web page classifiers for focused crawlers and also explores the impact of web-based feature in collaboration with web classifier. It also evaluates the performance of classification technique such as Support vector machine, Naive Bayes, Linear Regression and Random Forest over web page classification. Along with that it examines the impact of web feature i.e. anchor text, Page content and link over web page classification. Finally the paper yield interesting result about the collective response of web feature and classification technique for web page classification as a relevant class and irrelevant class.