An Efficient Information Extraction Mechanism with Page Ranking and a Classification Strategy based on Similarity Learning of Web Text Documents

Abstract

Users have recently had more access to information thanks to the growth of the www information system. In these situations, search engines have developed into an essential tool for consumers to find information in a big space. The difficulty of handling this wealth of knowledge grows more difficult every day. Although search engines are crucial for information gathering, many of the results they offer are not required by the user because they are ranked according on user string matches. As a result, there were semantic disparities between the terms used in the user inquiry and the importance of catch phrases in the results. The problem of grouping relevant information into categories of related topics hasn't been solved. A Ranking Based Similarity Learning Approach and SVM based classification frame work of web text to estimate the semantic comparison between words to improve extraction of information is proposed in the work. The results of the experiment suggest improvisation in order to obtain better results by retrieving more relevant results.