International Journal of Modern Engineering Research (IJMER)
In this paper, the authors have introduced a concept of capturing different web log file, while the user is accessing the distance education system website. Web log file can be further used in pattern discovery and pattern analysis process. Web log file is saved in text (.txt) format with \"Comma\" separated attributes. Log files can't be directly used for pattern discovery process because it consists of irrelevant and inconsistent access information. Therefore there is need of Web log preprocessing which includes different techniques such as field extraction, data cleaning, data filtering, and data summarization. They have discussed different types of web log files and preprocessing techniques.