An Artificial Neural Network Approach for Classifying E-Commerce Web Pages

I. Anagnostopoulos, G. Kouzas, C.Anagnostopoulos, I. Psoroulas, D. Vergados, V. Loumos, and E. Kayaf


Information system, Artificial Neural Network, web page classification, e-commerce.


In this paper, an information system capable of identifying and categorizing e-commerce web pages is proposed, on the basis of information filtering combined with a Artificial Neural Network (ANN). It includes term transformation techniques along with pattern recognition methods for content identification. The information representation techniques are based on a multi-dimensional descriptor vector with 432 word stems collected either manually or in an automatic way. This vector is called e-Commerce Descriptor Vector (e-CDV) and when applied in a proper way according to a proposed technique, it assigns a unique profile to every tested web page. The created profile is then considered as a pattern, and it is categorized by the system according the Business Media Framework (BMF). The system classifies twelve classes of web pages. Eleven of them follow the concepts of the BMF, while the last represents all the other web pages.

Important Links:

Go Back