Mining User Interests from Web Log Data using Long-Period Extracting Algorithm

Abstract

The knowledge available on the Web is increasing rapidly. Without using a recommendation system, many users spend a lot of time on the Web to get the data they need. Using a recommendation system is very important as it reduces the time that users need to spend to get the data they need. But, nowadays many recommendation systems cannot give the exact information to the users. The reason is that they cannot extract user’s interests accurately. So, analyzing the user’s interests and identifying the correct domain is an important research
in Web Usage Mining. If users' interests can be automatically detected from their Web Log Data, they can be used for information recommendation which will be useful for both the users and the website developers. In this paper, a unique algorithm is proposed to extract users' interests. The algorithm is based on visit time and visit density. The experimental results of the proposed method find the user's interested domains.