Hybrid Approach to Improve Web Site Design based on Web Log Mining

As we see many websites have a hierarchical organization of content. This organization may be quite different from the organization expected by visitors to the website and sometime it is unclear where a specific document is located. There are many algorithms that automatically search pages in a website whose location is different from where visitors expect to find them. In the above case visitors will backtrack if they do not find the information where they expect it. In this paper an algorithm is present for discovering such expected locations. Expected locations with a significant number of hits are then presented to the website administrator. We also present an algorithm for selecting expected locations (for adding navigation links) to optimize the benefit to the website or the visitor. Beside the structure of the website, users' preference to target pages is another key factor for analyzing the location or node importance. Clearly a specific document which is visited frequently or where users stay for a long while indicates that it has a higher degree of preference. This paper introduces the duration’s as a weight of the node to measure the preference.