Mining Semantic Web Data Using K-means Clustering Algorithm
Wria Mohammed Salih Mohammed
School of Basic Education, Computer Science, University of Sulaimani, Kurdistan, Iraq.
Mohamad Mehdi Saraee *
Islamic Azad University, Shahreza Branch, Shahreza, Islamic Republic of Iran.
*Author to whom correspondence should be addressed.
Abstract
The combination between semantic web and web mining is known as semantic web mining. Semantic web can improve the effectiveness of web mining. The knowledge of semantic web data can be mined using web mining techniques, as semantic web data are rich sources of knowledge to feed data mining techniques. This paper concentrated on how to combine two emergency research areas, namely semantic web and web mining. Firstly, we extract data from RDF file using SPARQL as query language. After that, we are going to cluster the entities of semantic web. One of the techniques is k-means clustering algorithm. Sematic web is about the meaning of the web data and to make machine understandable about it. Moreover, web mining is to extract and discover useful and previously unknown information from web data. This research gives an overview of where semantic web and web mining areas meet today, and how it is useful to combine these two well-known areas to obtain better and more accurate results.
Keywords: Data mining, semantic web, cluster, k-means.