About CAFÉ

With support from USAID and the Development Impact Lab at UC Berkeley, the CITRIS Data and Democracy Initiative is developing a new social media platform that directly engages citizens and communities from developing regions to collectively assess conditions, needs, and outcomes related to engineering innovations in humanitarian assistance, solar energy, democracy and governance, and global health.

In contrast to polls and surveys that are extremely valuable for analysts, CAFÉ is user-facing: the CAFÉ platform will provide direct, immediate visual feedback to participants, allowing them to instantly understand where they stand on key issues with respect to other participants, and encourage open-ended qualitative responses that can enhance interaction between users. Like a coffeehouse, we envision CAFÉ as a grassroots, user-friendly, self-organizing environment that allows the wisdom of crowds to identify, highlight, and display patterns, trends, and insights as they emerge. To facilitate interactions, CAFÉ will incorporate techniques from deliberative polling, collaborative filtering, and multidimensional visualization.

Opinion Space, a precursor to CAFÉ that focused on social innovation, has been used since 2010 by the U.S. State Department. Thousands of participants from around the world use it to organize, visualize, and analyze constructive suggestions on foreign policy:

"Opinion Space will harness the power of connection technologies to provide a unique forum for international dialogue. This is … an opportunity to extend our engagement beyond the halls of government directly to the people of the world."
U.S. Secretary of State Hillary Clinton (2010)

Recent Papers

  1. Using a Social Media Platform to Explore How Social Media Can Enhance Primary and Secondary Learning. Sanjay Krishnan, Yuko Okubo, Kanji Uchino, and Ken Goldberg. Learning International Networks Consortium (LINC) 2013 Conference. MIT, Cambridge, MA. June 2013. [.pdf]

  2. Distributed Spectral Dimensionality Reduction for Visualizing Textual Data. Sanjay Krishnan and Ken Goldberg. International Conference on Machine Learning (ICML) Workshop on Spectral Learning Methods, Atlanta, GA, June 2013. [.pdf]

Available for download from: http://goldberg.berkeley.edu/pubs/

Developer Resources

Malasakit is a variant of CAFÉ originally intended for assessing disaster risk reduction strategies in the Phillipines. Malasakit was developed and deployed through a partnership between UC Berkeley and National University in the Phillipines through the Philippine-California Advanced Research Institutes (PCARI) Project.

However, Malasakit can be applied to a variety of domains, and has been designed with the open-source community in mind. The following resources are available to anyone who would like to contribute to the project:

Contact Information

For inquiries, please contact:

  • Ken Goldberg
    William S. Floyd Jr. Distinguished Chair in Engineering, UC Berkeley
    craigslist Distinguished Professor of New Media
    Chair and Professor, Industrial Engineering / Operations Research (IEOR) Dept.
    Director, AUTOLAB and CITRIS "People and Robots" Initiative
    Founding Member, Berkeley AI Research (BAIR) Lab
    Joint Appointments: EECS, Art Practice, School of Information (UC Berkeley) and Radiation Oncology (UC San Francisco Medical School)

    IEOR Chair Office: 4143 Etcheverry Hall, Faculty Office: 425 Sutardja Dai Hall
    Berkeley, CA 94720-1758
    Twitter: @Ken_Goldberg ∣ G+: http://j.mp/Ken_Goldberg
    (510) 643-9565goldberg@berkeley.eduhttp://goldberg.berkeley.edu

  • Brandie Nonnecke, PhD
    Program Manager, CITRIS and the Banatao Institute, UC Berkeley