Web page classification based on a simplified swarm optimization

Abstract

Owing to the incredible increase in the amount of information on the World Wide Web, there is a strong need for an efficient web page classification to retrieve useful information quickly. In this paper, we propose a novel simplified swarm optimization (SSO) to learn the best weights for every feature in the training dataset and adopt the best weights to classify the new web pages in the testing dataset. Moreover, the parameter settings play an important role in the update mechanism of the SSO so that we utilize a Taguchi method to determine the parameter settings. In order to demonstrate the effectiveness of the algorithm, we compare its performance with that of the well-known genetic algorithm (GA), Bayesian classifier, and K-nearest neighbor (KNN) classifiers according to four datasets. The experimental results indicate that the SSO yields better performance than the other three approaches.