Data Mining and Knowledge Engineering

Vikrant Sabnis ¹, R. S. Thakur ¹

Affiliations
1 Department of Computer Applications, Maulana Azad National Institute of Technology, Bhopal, M.P., IN

Abstract

With increase in network technologies and number of users working on the network, attempts are being made to discover the useful knowledge from the secondary data. For retrieving knowledge large number of models, techniques and methods are evolving continuously in the area of web content mining. These techniques are becoming very critical for effective management of web sites in the variety of domains such as business, education and e-learning. Based on the prediction approach the user browsing behaviors can be guessed and this information can be utilized for building of proper web sites. This paper proposes star schema for web contents mining from the complex data which is multidimensional in nature. Further the association among web contents is explored using multidimensional ARM approach to know the surfing behavior of web users. At the end Performance computation of proposed work has been discussed, which shows improvement in the gain and implementation explains well the significance of multidimensional association rule in web content data. The paper also compares pros and cons with the traditional state of art approaches.

Keywords

Web Content Mining, Data Mining, Pattern Discovery.

Full Text

     

Vikrant Sabnis ¹, Neelu Khare ¹, R. S. Thakur ¹, K. R. Pardasani ²

Affiliations
1 Department of Computer Applications, Maulana Azad National Institute of Technology, Bhopal, M.P, IN
2 Department of Mathematics, Maulana Azad National Institute of Technology, Bhopal, M.P, IN

Abstract

Web content mining refers to description and discovery of useful information from the web contents/data/documents. Hypertext is one of the most common web content data that has hyperlinks in addition to text. These are modeled with multiple levels of details depending on the application. In this paper Karnaugh map model for multilevel association rule mining has been developed to investigate association relationships among hypertexts of a web site. Karnaugh map model needs single scan of data and stores the information in the form of frequency. Model adopts progressively deepening approach for finding large text sets by utilizing karnaugh map logic for finding frequent text sets at each level of abstraction. Frequent texts sets are generated by the karnaugh map model are used to discover strong association relationships among hypertexts at different levels of abstraction. Further the rules are categorized under three categories and their behavior is studied across the level of abstractions.

Keywords

Karnaugh Map Model, Multilevel Association Rules, Association Relationships, Frequent Text Set.

Full Text