RESEARCHER: Alfred Kobsa


Consumer studies have demonstrated that online users value personalized content. At the same time, providing personalization on websites is also profitable for web vendors. This win-win situation is however marred by privacy concerns since personalizing people's interaction entails gathering considerable amounts of data about them. As numerous recent surveys have consistently demonstrated, computer users are very concerned about their privacy on the Internet and are often unwilling to disclose personal data. Moreover, the collection of personal data is also subject to legal regulations in many countries and states, and sometimes to industry-specific self-regulation.

In a project that is supported by the National Science Foundation, Alfred Kobsa and his research group developed a novel privacy-enhancing user modeling architecture. The system takes users’ privacy concerns into account as well as the privacy laws and regulations that apply to each individual user. It then dynamically selects personalization methods during runtime that meet all privacy constraints. The results of this project have been published at top-ranked conferences, in book and handbook articles, and in the Communications of the ACM.