Intelligent Web Search Recommender System: An Application of Ensemble of Convolution Neural Network for Deep Semantic Content Analysis of Web Documents

Abstract

Web Information retrieval is widely used for retrieving web documents relevant to the user search query. Search engines retrieve huge collection of web documents for a given search query and an information overload problem arises for the web user.  Web page recommender systems are widely used to deal with the information overload problem. Quality of the web page recommendations for a given search query depends heavily on the document feature representation. In this research a novel method is explained for Intelligent web search based on deep semantic content analysis of clicked web documents using an ensemble of convolution neural network. Deep learning model Convolution neural network has been used in the research for feature generation and it effectively represents the text characterization for classification. The optimized web document feature vector is generated using the ensemble of CNN is finally averaged at the output layer for clustering. The resulting clusters of optimal web documents optimized feature vector therefore groups semantic similar web documents in a given cluster for web page recommendations during web search. Experiment results confirm the improvement in average precision to 93% across all selected domains that shows the relevant web documents are increased in the recommendations based on clusters of web document optimal feature vectors generated using ensemble of CNN. Thus, the proposed system performs the Intelligent web search recommendations based on the deep semantic deep content analysis of web documents using an ensemble of CNN.