The Usable Privacy Policy Project

Towards Effective Web Privacy Notice and Choice

Natural language privacy policies have become the de facto standard to address expectations of “notice and choice” on the Web. However, users generally do not read these policies and those who do struggle to understand them. Initiatives, such as P3P and Do Not Track aimed to address this problem by developing machine-readable formats to convey a website's data practices. However, many website operators are reluctant to embrace such approaches.
In the Usable Privacy Policy Project, we build on recent advances in natural language processing (NLP), privacy preference modeling, crowdsourcing, and privacy interface design in order to develop a practical framework based on a website's existing natural language privacy policy that empowers users to more meaningfully control their privacy, without requiring additional cooperation from website operators.Learn More

View our other videos. Our videos are hosted on YouTube. See YouTube's Privacy Policy here.

OPP-115 Corpus

The OPP-115 corpus consists of 115 privacy policies with 23K fine-grained data practice annotations. Learn more about our project's datasets and tools.

Use our interactive website to navigate privacy policy annotations extracted by both humans and machine learning techniques. Visit

Project Newsletter

Our project newsletter highlights our progress and activities over the past year. Read the newsletter.

Project Activities

The AAAI Spring Symposium on Privacy Enhancing AI and Language Technologies (PAL 2019) was held at Stanford University on March 25-27, 2019. Learn more about our project's activities.

This project is funded by the National Science Foundation under its Secure and Trustworthy Computing initiative (CNS-1330596 and CNS-1330214). This project is also supported in part by DARPA and the Air Force Research Laboratory under agreement number FA8750-15-2-0277. The US Government is authorized to reproduce and distribute reprints for Governmental purposes not withstanding any copyright notation thereon. The views and conclusions contained herein are those of the authors and should not be interpreted as necessarily representing the official policies or endorsements, either expressed or implied, of DARPA, the Air Force Research Laboratory, the NSF or the US Government.