Mining Navigation Patterns in a Virtual Campus

Abstract

The web designers of Virtual Campuses or web applications, in general, targeting a large number of online users aim to facilitate the navigation of users through the site content. Qualitative and quantitative studies can support web designers by providing information on users' profiles, interest on site content, etc. One source of valuable information is that of server log files, which record users' action during online navigation. The study of user behavior through actions recorded in these logs allows, in particular, the identification of navigation patterns. In this paper we present the processing and analysis of log data files of a Virtual Campus. The pre-processing of the log data files is done through a Java implementation that generates a file structure and content suitable for data mining. We have selected WEKA framework, which thanks to the KMeans, Apriori and FPGrown algorithms, makes possible to obtain navigation patterns of users of the Virtual Campus. The study is motivated and conducted in the context of the actual data logs of the Virtual Campus of Open University of Catalonia.