International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395 -0056
Volume: 04 Issue: 04 | Apr -2017
p-ISSN: 2395-0072
www.irjet.net
A Novel Approach to Analyse User Satisfaction Level On Web pages using Ontologies Dr. S. Chitra Associate Professor, Department of Computer Science, Government Arts College (Autonomous), Coimbatore – 641 018, Tamilnadu, India ---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - Web access log analysis is to analyze the
patterns of web site usage and the features of user’s behavior. The proposed method constructs sessions as a Directed Acyclic Graph which contains pages with calculated weights. This will help site administrators to find the interesting pages for users and to redesign their web pages. After Session Construction a web usage analysis is used for finding the correlation between consumer emotions and buying behaviors. A semantic web usage mining technique is proposed for finding web access patterns from the annotated web usage logs. It includes consumer emotions and behaviors via self-reporting and behavioral tracking. To signify the real-time temporal concepts and requested resource attributes of periodic pattern based web access activities fuzzy logic is used. The consumer emotions and behaviors are integrated into a Personal Web Usage Lattice which represents the web access activities. From this we create Personal Web usage Ontology which facilitates semantic web applications. But the limitation is less efficient in terms of accuracy and user satisfaction level. So, in this manuscript an innovative technique is introduced which is called Optimum Session Interval based Particle Swarm Optimization(OSIPSO). This technique is used to find the optimum session interval. Additionally, an associative classification is used to enhance the level of accuracy. Associative classification is a combination of associative rule mining and classification rule mining. An experimental result shows that the proposed work achieves high accuracy and highly efficient in terms of user satisfaction level. Key Words: Session Construction, Directed Acyclic Graph (DAG), Robots Cleaning, Emotion and behavior profiling, ontology generation, semantic web, Particle swarm optimization, Associative classification 1. INTRODUCTION This work is partitioned into 2 phases, namely Phase I : Preprocessing of logs Phase II : Analysis of user satisfaction level of the web pages. Phase I : Preprocessing of logs
each of which is sent to a web server whenever a user sent a request. Web usage mining extracts regularities of user access behaviour as patterns, which are defined by combinations, orders or structures of the pages accessed by the internet. Web usage mining consists of three main steps: Data Preprocessing Knowledge Extraction Analysis of Extracted Results Preprocessing is a significant step since the Web architecture is very complex in nature and 80% of the mining process is done at this phase. Graph and traversal are extensively used to model a number of classes of real world problems. For example, the structure of Web site can be modelled as a graph in which the vertices represent Web pages, and the edges correspond to hyperlinks between the pages [1]. Mining using graphs turns out to be a centre of interest. Traversals on the graphs are the models of User navigations on the Web site [2]. Once a graph and its traversals are specified, important information can be discovered. This paper provides a new version to the previous works by considering weights attached to the vertices of graph. Such vertex weight may reflect the importance of vertex. For example, each Web page may have different consequence which reflects the value of its contents. Phase II : Analysis of user satisfaction level on the web pages. Web usage mining is an automatic detection of patterns in clickstreams and related data collected as a result of user relations with one or more Web sites. The main intent of web usage mining is to examine the behavioral patterns and profiles of users interacting with a web site. The discovered patterns are generally characterized as collection of pages, objects or resources which are regularly accessed by groups of users with common interests. Human emotions are a significant factor of human behaviors in web mining analysis [3]. The relationships between consumer emotions and their buying behaviors have been well recognized [4] [5].
A web access log is a time series record of user’s requests © 2017, IRJET
|
Impact Factor value: 5.181
|
ISO 9001:2008 Certified Journal
|
Page 294