A Method for Extracting Information from the Web Using Deep Learning Algorithm

Web mining related research are getting more important now a days because of the reason that large amount of data are managed through internet. The web usage is increasing in an uncontrolled manner. A specific system is needed for controlling such large amount of data in the web space. The web mining is classified into three major divisions that are web content mining, web usage mining and web structure mining. In this paper, we propose a web content mining approach based on a deep learning algorithm. The deep learning algorithm provides the advantage over Bayesian networks because Bayesian network is not following in any learning architecture like proposed technique. In the proposed approach, three features are considered for extracting the web content. The features used are concept feature, deals with the semantic relations in the web, format feature, deals with format of the content and title feature, deals with the web tittle. The above listed feature produces some model parameters, which is given as the input to the deep learning algorithm. The experimental analysis showed that, the proposed approach is efficient in web content extraction. The average precision, recall and f-measure values are updated as 83.875%, 78.3% and 80.83% respectively.