Navigation pattern discovery on Web site based on the distance between sequences

Abstract

Web usage Mining is an application of data mining algorithm to Web logs to find trends and regularities in Web user's navigation patterns. The results of Web Usage Mining have been used to improve Web site design, and Web server system performance. In this article, an improved Ward's method is proposed for web user clustering. In the proposed method, distance between elements is a no-Euclidean distance measure. Experiments show that the proposed algorithm clustering web users effectively compared with the association measure.