Web Proxy Log Data Mining System for Clustering Users and Search Keywords

Abstract

In this study, Internet users were clustered by the search keywords which they type into search bars of searchengines. Our proposed software is called UQCS (User Queries Clustering System) and it is developed todemonstrate the efficiency of our hypothesis. UQCS co-operates with the Strehl’s relationship based clusteringtoolkit and performs segmentation on users based on the keywords they use for searching the web. Internet Proxyserver logs were parsed and query strings were extracted from the search engine URL’s and the resulting IP-Termmatrix was converted into a similarity matrix using Euclidean, Jaccard, Cosine Distance and Pearson CorrelationDistance metrics. K- Means and graph-based OPOSSUM algorithm were used to perform clustering on thesimilarity matrices. Results were illustrated by using CLUSION visualization toolkit.