Abstract— In the last decade, many data mining techniques have been proposed for fulfilling various knowledge discovery tasks in order to achieve the goal of retrieving useful information for users. Data mining techniques include association rule mining, frequent itemset mining, sequential pattern mining, maximum pattern mining and closed pattern mining. However, how to effectively exploit the discovered patterns is still an open research issue, especially in the domain of Web mining. In this study, we compare these data mining methods based on the use of several types of discovered patterns. The performance of the pattern mining algorithms is investigated on the Reuters dataset RCV1 for completing Web mining tasks. The experimental results show that the closed pattern methods, such as SCPM and NSCPM, have better performance due to the use of pruning mechanism in the pattern discovery stage.

Index Terms— Web mining, data mining, pattern taxonomy model.

Sheng-Tang Wu is with the Department of Applied Informatics and Multimedia, Asia University, Taichung, Taiwan (e-mail: swu@ asia.edu.tw).
Yuefeng Li is with the Faculty of Science and Engineering, Queensland University of Technology, Brisbane, Australia (e-mail: y2.li@qut.edu.au).

Cite: Sheng-Tang Wu and Yuefeng Li, " Pattern-Based Web Mining Using Data Mining Techniques," International Journal of e-Education, e-Business, e-Management and e-Learning vol. 3, no. 2, pp. 163-167, 2013.