A Novel Semantically-Time-Referrer based Approach of Web Usage Mining for Improved Sessionization in Pre-Processing of Web Log
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2017, Vol 8, Issue 1
Abstract
Web usage mining(WUM) , also known as Web Log Mining is the application of Data Mining techniques, which are applied on large volume of data to extract useful and interesting user behaviour patterns from web logs, in order to improve web based applications. This paper aims to improve the data discovery by mining the usage data from log files. In this paper the work is done in three phases. First and second phase0 which are data cleaning and user identification respectively are completed using traditional methods. The third phase, session identification is done using three different methods. The main focus of this paper is on sessionization of log file which is a critical step for extracting usage patterns. The proposed referrer-time and Semantically-time-referrer methods overcome the limitations of traditional methods. The main advantage of pre-processing model presented in this paper over other methods is that it can process text or excel log file of any format. The experiments are performed on three different log files which indicate that the proposed semantically-time-referrer based heuristic approach achieves better results than the traditional time and Referrer-time based methods. The proposed methods are not complex to use. Web log file is collected from different servers and contains the public information of visitors. In addition, this paper also discusses different types of web log formats.
Authors and Affiliations
Navjot Kaur, Himanshu Aggarwal
Keywords
Related Articles
- EP ID EP249761
- DOI 10.14569/IJACSA.2017.080122
- Views 99
- Downloads 0
Hybrid Ensemble Framework for Heart Disease Detection and Prediction
Data mining techniques have been widely used in clinical decision support systems for detection and prediction of various diseases. As heart disease is the leading cause of death for both men and women, detection and pre...
A New Approach of Digital Forensic Model for Digital Foic rensInvestigation
The research introduces a structured and consistent approach for digital forensic investigation. Digital forensic science provides tools, techniques and scientifically proven methods that can be used to acquire and...
Comparative Study in Performance for Subcarrier Mapping in Uplink 4G-LTE under Different Channel Cases
In recent years, wireless communication has experienced a rapid growth and it promises to become a globally important infrastructure. One common design approach in fourth generation 4G systems is Single Carrier Frequency...
Plant Leaf Recognition using Shape based Features and Neural Network classifiers
This paper proposes an automated system for recognizing plant species based on leaf images. Plant leaf images corresponding to three plant types, are analyzed using two different shape modeling techniques, the first base...
An Advanced Emergency Warning Message Scheme based on Vehicles Speed and Traffic Densities
In intelligent transportation systems, broadcasting Warning Messages (WMs) by Vehicular Ad hoc Networks (VANETs) communication is a significant task. Designing efficient dissemination schemes for fast and reliable delive...