Conclusions and Future Work

We have presented a general framework for personalization based on usage and content mining, in which the user preference is automatically learned from Web usage data and integrated with domain knowledge and the site content. This has the potential of eliminating subjectivity from profile data as well as keeping it up-to-date. Furthermore, the integration of usage and content mining increases the usefulness and accuracy of the resulting recommendations. Our experimental results indicate that the techniques discussed here are promising, each with its own unique characteristics, and bear further investigation and development. Our future work in this area will include automatic classification of pageview types and better integration of a variety of pageview types (such as those representing different e-commerce or product-oriented events) into the mining and recommendation process.