An improved Naive Bayesian algorithm for Web page text classification

This paper studies the process and methods of text classification. Based on Naive Bayesian algorithm and the semi-structured feature in Web page information, this paper proposes an improved Algorithm for Web page text Information classification which utilizes Html tag Information in classification. Experiments show that this algorithm is feasible and effective and can apply to information extraction in topic search engine, which can enhance the theme fitness of the search results and further improve the searching efficiency.