Pre-processing of Web Logs for Mining World Wide Web Browsing Patterns

Web usage mining is a type of web mining, which exploits data mining techniques to extract required information from navigational behaviour of WWW users. Hence the data must be preprocessed to improve the efficiency and ease of the mining process. So it is important to pre-process before applying data mining techniques to discover user access patterns from web logs. The main task of data pre-processing is to remove noisy and irrelevant data, and to reduce data size for the pattern discovery phase. This paper mainly focus on the first phase of web usage mining i.e data preprocessing with activities like field extraction and data cleaning algorithms. Field extraction algorithm used for separating the single line of the web log file into fields. Data cleaning algorithm eliminates the inconsistent and unnecessary items in the analyzed data.