Methodology Design for Data Preparation in the Process of Discovering Patterns of Web Users Behaviour

Abstract

Discovering of behaviour patterns of website visitors is one of the most common applications in web log mining. Based on the discovered users' behaviour patterns, it is possible to restructure or in combination with other knowledge personalize the examined website, portal or other web-based system. Data preparation represents the first inevitable step in the process of discovering users' behavioural patterns. In this paper we summarize the results of our previous research, where we carefully examined the relevance of individual steps of data preparation from a web server log file and virtual learning environment for further analysis. The aim of our experiments was to find out to what extent it is necessary to realize the time-consuming data preparation in the process of discovering patterns of behaviour of web users and to determine the inevitable steps to obtain reliable data from different types of log files. Considering the obtained results we propose a methodology for data preparation in the process of discovering patterns of web user behaviour based on the results of experiments we carried out. The research results showed, that in the case of systems providing sophisticated navigation options and a rigid structure of the content (which is characteristic for the most virtual learning environments), the paths completing is not an inevitable step in data preparation in the process of discovering patterns of web users' behaviour.