Core Data Science

    KDD Brings Together the top Data Science Minds
    by Kelly Berschauerمنذ حوالي شهر
    Core Data Science
    Blog
    Over 30 Facebook and Instagram researchers, engineers, recruiters and academic relations team members are on hand at KDD 2016 in San Francisco, CA this week.
    Cat People, Dog People
    by Moira Burke, Lada Adamic, Amaç Herdağdelen, Dirk Neumannمنذ حوالي شهر
    Core Data Science
    Blog
    Are you a cat person or a dog person? In honor of International Cat Day on August 8 (sorry dogs), we wanted to understand more about the social characteristics of these two camps of animal lovers.
    Imperfect Treatment Assignments
    by Dominic Coey, Michael Baileyمنذ حوالي ‏3‏ أشهر
    Core Data Science
    Blog
    Running audience-level tests is ideal, but is often tricky to achieve.
    How blind people interact with visual content on social networking sites
    by Shaomei Wuمنذ حوالي ‏6‏ أشهر
    Core Data Science
    Blog
    We conducted a study with Cornell University to better understand the blind community's experience with visual content. This study highlighted the challenges blind people face and the strategies they...

    Highlights

    KDD Brings Together the top Data Science Minds
    by Kelly BerschauerAugust 15, 2016
    Blog post
    Cat People, Dog People
    by Moira Burke, Lada Adamic, Amaç Herdağdelen, Dirk NeumannAugust 7, 2016
    Blog post

    About Core Data Science

    The Data Science team conducts large scale, quantitative research to gain deeper insights into how people interact with each other and with their world. To accomplish these goals, we also build scalable platforms for the collection, management, and analysis of data.

    Our findings inform decisions in areas critical to the success of the company, improve the experiences people have on the site, and are of broad external interest.

    Our research areas span a variety of disciplines, including machine learning, econometrics, social psychology, and statistical inference. We use mixed methods to accomplish these goals, including topic modeling, regression, network analysis, field experiments, surveys, and information visualization.

    Visit Data Science on Facebook

    Publications

    Towards Optimal Cardinality Estimation of Unions and Intersections with Sketches
    Daniel Ting
    ACM Conference on Knowledge Discovery and Data Mining (KDD 2016)
    Aug 12, 2016
    This paper presents and analyzes two new classes of methods for estimating cardinalities of intersections and unions from sketches
    The Relationship between Facebook Use and Well-Being Depends on Communication Type and Tie Strength
    Moira Burke, Robert Kraut
    Journal of Computer-Mediated Communication (JCMC)
    Jul 27, 2016
    An extensive literature shows that social relationships influence psychological well-being, but the underlying mechanisms remain unclear. We test...
    The Social Ties of Immigrant Communities in the United States
    Amaç Herdağdelen, Bogdan State, Lada Adamic, Winter Mason
    WEBSCI
    May 22, 2016
    In this paper we study the composition of Facebook social networks of people who have moved from one country to another.

    Blog

    KDD Brings Together the top Data Science Minds
    by Kelly BerschauerAug 15, 2016
    Cat People, Dog People
    by Moira Burke, Lada Adamic, Amaç Herdağdelen, Dirk NeumannAug 7, 2016
    Imperfect Treatment Assignments
    by Dominic Coey, Michael BaileyJun 21, 2016
    Facebook Researchers Focusing on the Future of Human Computer Interaction at CHI 2016
    by Mike Massimi, Vanessa Callison-Burch, Alex Dow, Lada Adamic, Vasanth Rajendran, Margaret Gould Stewart, Sean KellerMay 6, 2016

    Research Topics

    • Computational social science
    • Computer-mediated communication
    • Auction theory and mechanism design
    • Experimentation and statistical inference
    • Social influence and network externalities
    • User modeling
    • Machine learning
    • Well-being
    • ICT4D and population science



    Join Us

    Do you want to help more than a billion people all over the world connect and share?

    View Open Positions

    Code

    Learn about our open source tools and technologies, our challenging scaling experiences, and more.

    Go to Facebook Code