Web Usage Mining Using GSP Algorithm: A Study on Sultanah Bahiyah Library Online Databases

Application of data mining to the World Wide Web referred as Web mining is at the cross road of research from several research communities which can be divided into three
branches: Web Content Mining, Web Structure Mining and Web Usage Mining. Sultanah Bahiyah Library which is considered as one of the most important resources for University Utara Malaysia (UUM) students provides several online databases that can be utilized by its users in seeking the needed information. Analyzing the usage or access pattern of these databases is time consuming and is not an easy task because the number of users accessing the site every day are too many. The goals of this study are to propose a suitable technique for preprocessing web log data of Sultanah Bahiyah Library online databases that can reduce the file size and to analyze the user's access pattern of the
online databases using web usage mining. In this study web usage mining use sequential pattern technique with GSP algorithm. This study found out that Emeraldinsight was
visited most by 20% of the user. And the top three sequences were {Emeraldinsight, Epnet, Proquest-direct) with support = 16.6%.