Association based classification for relational data and its use in web mining

Classification based on mining association rules is a method with good accuracy and human readable classification model. The aim of this paper is to propose modification of the basic association based classification method, which can be used for the data extracted from Web pages. In this paper, the modifications of the method and necessary discretization of numeric attributes will be described. Next, the experiments with various data will be presented, with emphasis on data obtained by extraction and segmentation of web pages.