Combined mining of Web server logs and Web contents for classifying user navigation patterns and predicting users' future requests.

摘要

With the explosive growth of knowledge available on the World Wide Web, it becomes much more difficult for users to access relevant information efficiently and it also presents a challenging task for web designers to organize site contents to meet the needs of users. Automatic classification of user navigation patterns provides a solution to these problems. In this thesis, we propose a novel approach to classifying user navigation patterns and predicting users' future requests using the N-gram-based user navigation profiles extracted by combined mining of Web server logs and web contents. We have applied the approach to build an experimental system. The performance of the system is evaluated based on both classification and prediction accuracy. Our system achieves the classification accuracy of nearly 70% and the prediction accuracy of about 65%, which is comparable to the state-of-the-art systems. This approach may be used to facilitate better web personalization and website organization.