Abstract: In our online interactions and consumptions, we are faced with a deluge of decisions. As we use our smartphones and social networks, for example, we are required to make an absolutely horrifying number of privacy decisions. This is only expected to get worse as more of our devices and appliances join the Internet of Things. In this talk, I will demonstrate how my research team is creating and testing user-adaptive systems that support users' privacy decision-making practices. These systems leverage machine learning techniques to predict users' privacy preferences and behaviors based on their past behavior and known characteristics, and then adapt their privacy settings and/or the settings interface to these preferences.

User-tailored systems are not without limitations, though. The filter bubble, for example, suggests that automation may be gradually replacing users' innate creativity and understanding. To combat this problem, my team aims to develop user-adaptive systems for Self-Actualization: systems that help users in developing, exploring, and understanding their unique personal tastes. To do this, we 'subvert' existing machine learning algorithms to give them a stronger focus on supporting (rather than replacing) users' decision-making processes, on exploration rather than consumption, and on covering all (rather than some) of the users' tastes.

Combining these two streams of research, I will outline my future research plans to demonstrate how adaptively supporting users' decision processes can empower users to make better decisions---in the area of privacy and beyond.

Short Bio: Bart Knijnenburg is an Associate Professor in Human-Centered Computing at the Clemson University School of Computing, where he co-directs the Humans and Technology lab. He holds a B.S. in Innovation Sciences and an M.S. in Human-Technology Interaction from the Eindhoven University of Technology, The Netherlands, an M.A. in Human-Computer Interaction from Carnegie Mellon University, and a Ph.D. in Information and Computer Sciences from the University of California, Irvine. Bart works on privacy decision-making and user-centric evaluation of adaptive systems. His research has been awarded over $2M in funding from the National Science Foundation (including a CAREER award), the Department of Defense, the Department of Education, and corporate sponsors.