A Two-Level KNN Based Teaching Web Pages Classification Model

Web classification is considered to be an important and challenging task, it has extracted more and more research work in recent years. Due to domain diversity and complexity, there remain many problems not solved. This work is focus on teaching web page classification and a novel two-level classification model is proposed. Its processing including two steps: at first, the model employ global feature vector to recognize the content web page whether related to education, and then, the specific subject of education page were be identified in the second level by utilize the difference feature vector. The experiments show that the correct classification rate is improved, and the detailed result are listed in the end of this paper.