Automatically Answering People’s Privacy Questions: Weaving Together User-Centered Design, Natural Language and Legal Consideration
Through a grant awarded by the National Science Foundation as part of the NSF’s Secure and Trustworthy Cyberspace project, Fordham CLIP is collaborating with researchers at Carnegie Mellon University and Stanford University to develop privacy assistant functionality capable of answering privacy questions that actually matter to users. The project brings together from the three universities an interdisciplinary team of experts from technology, linguistics, and law. The team develop tools that combine natural language processing, machine learning, and crowdsourcing to investigate, design, and develop technologies for user‐centered privacy dialogs that focus on informing users about the issues that matter to them and on enabling them to selectively explore those issues through question answering functionality. Under the leadership of Principal Investigator Norton, the CLIP team provides a legal perspective on key features of website privacy policies, project surveys of users, and the development of new technological tools. Ultimately, the joint research team envisions the development of a chatbot-type tool that automatically answers questions users have about specific online services' privacy policies and practices.
Publications, Conferences, and Appearances
- Abhilasha Ravichander, Alan W Black, Shomir Wilson, Thomas Norton and Norman Sadeh, "Question Answering for Privacy Policies: Combining Computational and Legal Perspectives," 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP 2019) (Hong Kong, China)