Study of Different Focused Web Crawler to Search Domain Specific Information

Abstract

In human life, use of correct medicinal plant for treating diseases is very important. Medicinal plant is the important part of the Indian Ayurvedic system. So there is a need of heuristic search of medicinal plants over India. The huge amount of information related to medicinal plants is available on World Wide Web. For collecting such domain specific information from the internet, focused web crawler is useful. This paper proposed an efficient focused web crawler using hybrid model of Naïve Bayes classifier and Decision tree classifier. The result of classifier defines that web page is relevant or not relevant. The proposed hybrid classification will improve the accuracy of web crawling.