Paper Title
Web Content Mining Classification using Different Classifiers

Abstract
A rich verity of information and data is generated each day in online sources. The manual analysis and utilization of knowledge is a complex task, thus we need new generation analytics techniques that refine and provide impure information. Such techniques can help in various different areas of applications such as education, research, and others. Therefore the improvement on existing techniques in order to enhance the productivity of the existing methods is also a considerable effort. Thus the proposed work is motivated to explore the existing applications of web data mining and their importance in real world. Therefore first the different techniques of web content mining are investigated and using experimental analysis the effective feature selection and supervised learning algorithms are identified. Thus the selected two feature selection techniques GINI Index and Information Gain are utilized with the three popular supervised learning classifiers namely SVM (Support Vector Machine), SVR (Support Vector Regression) and k-NN (k-Nearest Neighbor). The comparative performance study demonstrates the SVM and SVR is superior classifier as compared to k-NN. Keywords - Web Data Mining, Feature Selection Techniques, Classification Techniques.