submitted in partial satisfaction of the requirements for the degree of DOCTOR OF PHILOSOPHY

OF THE DISSERTATION A Framework for Privacy-Enhanced Personalization By Yang Wang Doctor of Philosophy in Information and Computer Science University of California, Irvine, 2010 Professor Alfred Kobsa, Chair Web personalization has demonstrated to be advantageous for both online customers and vendors. However, its benefits may be severely counteracted by privacy constraints. Personalized systems need to address these privacy constraints, including users’ personal privacy preferences as well as privacy laws and industry self-regulations that may be in effect. This research aims to reconcile privacy and web personalization. In particular, this research proposes user-tailored privacy enforcement in personalization, i.e., catering privacy to the situation of each individual user. This research develops a framework for privacy-enhanced personalization based on product line architecture (PLA). This framework provides a systematic and flexible way to model, manage and enforce applicable privacy constraints in web personalization. Our systematic analysis of over 40 privacy laws shows that these legal requirements can not only affect the collection, storage and transfer of personal data, but also the methods that may be used to process the data in personalized systems. This framework dynamically selects and de-selects personalization methods during runtime in observance of each user’s applicable privacy constraints. A controlled experiment shows that users value the user-tailored privacy enforcement in personalization: they have higher regard for the privacy practices of a personalized system, disclose more information about themselves to the system, and do not perceive less per-