Web Content Classification using Content Features and Ant Colony Optimization Algorithm

The web content classification systemclassifies the noise or content from HTML web pages.The system proposes the Content Extractionalgorithm using content features to remove theboilerplate and to extract the main content from theweb page. After observation the HTML tags, one linemay not contain a piece of complete information andlong texts are distributed in close lines, this systemuses Text-Block Concept to determine the distance ofany two neighbor lines with text and FeatureExtraction such as Text Density (TD), anchor AnchorLink Density (ALD) and a new feature Title KeywordsDensity (TKD) classifies noise or content. Afterextracting the features, the system uses the C4.8decision tree method to classify the block is content ornon-content by using above features. After extractingthe main contents, the system uses a newclassification algorithm, Ant Colony Algorithm(ACO) that is able to solve discrete problems anddiscreteness of text document’s features. Texts areclassified by crawling of class population ants whichhave class information with them to find an optimalpath matching during it iterates in the algorithm.Finally, the system gains more interest as the classifier improves its performance with experience