Data Preprocessing and Cleansing in Web Log on Ontology for Enhanced Decision Making

Background/Objectives: Web applications are growing at a massive promptness and its users rise at exponential speed. The deviations in technology have made it potential to capture the user’s essence and interactions with web applications through web log file. Methods/Statistical Analysis: Due to huge amount of extraneous data in the web log, the original log file cannot be openly used in the Web Usage Mining (WUM) system. The web server log files used for mining several expedient patterns to analyze the access behavior of the user. Data pre-processing plays a dynamic role in Data Mining. Findings: We propose a new web log mining method for determining web access procedure from interpreted web usage logs which integrates data on user behaviors through self-rating and communication tracking. The raw data is preprocessed in order to improve the quality of data to be extracted. We discuss the significance of information pre-processing method and abundant steps elaborate in receiving the essential information effectively. This pre-processing method used to process and analysis the web log data for extraction of user search patterns. The fuzzy association rule minimizes users’ exploration period and facilitate for enhance decision making. Applications/Improvements: The proposed data cleaning method removes the extraneous records from web log. With this progression, we create a Personalized Ontology, which assists various semantic web applications such as site perfection, business intelligence and recommendations for behavioral analysis. Finally, we illustrate the efficiency of this method by the experimental results in the framework of data pre-processing and cleansing extraneous data for personalized ontology.