Algorithm Research on User Interests Extracting via Web Log Data

The information on the Web is growing dramatically. Without a recommendation system, the users may spend lots of time on the Web in finding the information they are interested in. Today, many Web recommendation systems can not give users enough personalized help but provide the user with lots of irrelevant information. One of the main reasons is that it can´t accurately extract user´s interests. Therefore, analyzing users´ Web log data and extracting users´ potential interested domains become very important and challenging research topics of Web usage mining. If users´ interests can be automatically detected from users´ Web log data, they can be used for information recommendation and marketing which are useful for both users and Web site developers. In this paper, we present some novel algorithms to mine users´ interests. The algorithms are based on visit time and visit density which can be obtained from an analysis of web users ´Web log data. Experimental results show that our new methods succeed in finding user´s interested domains.