Personal Data, Personal Benefits
Deborah Estrin, Computer Science, Cornell Tech, and Mor Naaman, Information Science, Cornell Tech, are working to create a future in which hyper-personalized content, online services, and personal information management tools let individuals benefit from their digital traces (such as location, communication, browsing, purchasing, and social media history) more directly, selectively, and transparently. Individuals will then be empowered to gain insights into their behavior, personalize their experiences, and more effectively utilize services to achieve their goals. Systems that engage users with the data they generate can promote selective sharing of personal information, giving users more control over their data-sharing and privacy.
To achieve these ends, Estrin and Naaman are developing novel user modeling techniques, policy-aware systems, and rich, user interactions. A particular focus is to improve systems that use individuals’ data in order to make more personally-relevant recommendations while limiting privacy exposure and increasing recommendation diversity. The modeling techniques will analyze a broad range of data types to incorporate users’ diverse and idiosyncratic interests. New recommendation models and policy-aware software architecture will consist of open source building blocks designed to facilitate adoption of an approach that puts the individual at the center of their personalization.