Improving SVM on web content classification by document formulation

Web contents are going overwhelming today. The numerous online documents, webpages, e-books, etc. are much useful but obtaining them is also time-consuming. Text categorization is one of the solutions to the issue. For all text categorization method, Support Vector Machines (SVM) is one of the most acceptable one. However, to perform more efficiently on webpages, it is necessary to add improvements on it. For webpages, the document title is meaningful as it is usually carefully created by editors and always shows the main content of the webpage. In this paper, an improvement of Support Vector Machine is proposed. The Document Representation for SVM emphases the features in documents´ title which is always popular in webpages and obviously contains essential contextual information for the documents.