ABSTRACT

As more organization rely on the Internet and the World Wide Web to conduct business, the proposed strategies and techniques for market analysis need to be revisited in this context. We therefore present a survey of the most recent work in the field of Web usage mining, focusing on three different approaches towards web logs clustering. Clustering analysis is a widely used data mining algorithm which is a process of partitioning a set of data objects into a number of object clusters, where each data object shares the high similarity with the other objects within the same cluster but is quite dissimilar to objects in other clusters. In this work we discuss three different approaches on web logs clustering, analyze their benefits and drawbacks. We finally conclude on the most efficient algorithm based on the results of experiments conducted with various web log files.