Abstrakt

WEB MINING: DOCUMENT FILTERING IN E-COMMERCE USING CLUSTERING

Ashok K. Panda, Dhiren K. Sahu, S.N.Dehuri, M.R.Patra

Document filtering is probably the most challenging task in the Web. Giving a prominent search result by filtering the document is a measure issue. Semantic similarity and large document clustering is the most difficult task as the web data has a lot of redundancy like outliers, missing values etc, data prepossessing is very much necessary. Search results produced by social search engine (web search) give more visibility to the content created. This paper focuses on semantic similarity measure, the F-measure for large document clustering. Document filtering is a task to retrieve documents relevant to user's profile. Generally, filtering systems calculate the similarity between the profile and each incoming document for retrieving documents with similarity having higher threshold value. With the increased use of the Internet and the World Wide Web, E-commerce transaction is growing rapidly. Therefore, finding useful patterns and rules of users� behaviours has become the critical issue for E-commerce and is used to tailor ecommerce services to meet the customers� need successfully. In this paper, we highlight the ArteCM clustering algorithm and implemented it which provides better results for document filtering for retrieving most relevant documents in E-commerce transaction.