期刊名称：International Journal of Computer Science & Technology
印刷版ISSN：2229-4333
电子版ISSN：0976-8491
出版年度：2013
卷号：4
期号：4
页码：287-290
语种：English
出版社：Ayushmaan Technologies
摘要：With the explosive growth of the World Wide Web, the amount of information available on-line is increasing rapidly. This certainly provides users with more options, but also makes it difficult to find the “right” or “interesting” information today. Web access log contains a lot of information about how the users explore the web. Mining this log, which is called Web Usage Mining, has been studied intensively these years. Web usage mining discovers user preference from this log and makes recommendations based on the extracted knowledge. More recently, a combination of web content, web structure and web usage mining has been studied and shows superior results in web recommendations. Clustering is a mechanism for filtering and grouping of data on the basis of certain characteristics such as time span, usage, occurrence etc. Clustering is a pivotal building block in many data mining applications and in machine learning. Classification of clustering algorithms can be done on multiple different aspects such as type of processing, data availability, Similarity of Data, Partitions, Center points etc. For this work, two types of processing has been considered 1) Off-line (batch) processing 2) Online or incremental Clustering. In Incremental clustering algorithm clusters data in dynamic form. Incremental Clustering requires initial clusters to be decided in advance i.e. they must pre exist for processing. If the initial clusters are to be fixed, then there are several ways it can be achieved. In this paper, we propose a new perspective of Web Usage Mining – mining the enterprise proxy log. Based on this, a novel WWWoriented web recommendation system, which we call EPWUM, is proposed and implemented.
