Support Vector Machine-Based Focused Crawler

The Internet is an immense source of information. People use search engines to find desired web pages. All these web pages are gathered from the search engine by using web crawler. In traditional crawler, the information retrieval was based on the occurrence of keywords in a document due to which many irrelevant web pages were also retrieved. For the effective classification of web pages, support vector machine (SVM)-based crawler model is proposed in this paper. Various features of URL and web page are used for effective classification. SVM is trained by using these features and further tested. The proposed model is analyzed using precision and recall metrics. The experimental results exhibit optimized results by using this proposed approach.