An Effective Web Usage Mining

Web usage mining is the area of data mining which deals with the discovery and analysis of usage patterns from web data, specifically web logs, in order to improve web based applications. Web usage mining consists of three find phases–, pre-processing, pattern discovery, and pattern analysis. After completion of these three phases the user can the required usage patterns and use these information for specific needs. Web log files are the primary data source for web usage mining. This usage analysis includes tasks like page access frequency, finding the common traversal paths through a website. These log files contains information that can’t be directly interpreted, for example information like who is accessing, which pages are accessing by whom, how much time user is accessing a particular page ,can’t be obtained directly these log files. Since log files are unformatted text files, they are complex to interpret and analyze. In this paper we propose a novel approach using universally accepted formatting language XML. In our approach text based log files are converted into XML format using parsers. Once a log file is in XML format, using DOM API or types of parser API’s we can retrieve the required information in an easy manner such as user and session identification and the paths that are frequently accessed. This paper presents several data preparation techniques based on XML parsers in order to increase the usability of websites.