Data Science Manager/Research Scientist at Facebook, research/data science support for Social Science One. Former (founding) Managing Director at Pew Research Center’s Data Labs.  Research interests: social media + news, political communication + representation, machine learning and experimentation, natural language processing and text as data.

More info: Google Scholar, Twitter, R-bloggers.
email: [firstname.lastname] AT gmail DOT com

Fun stuff: Blogposts on how politicians and constituents communicate on Facebook, a hackathonproject I worked on, and a recent Monkey Cage piece on skin complexion and campaigns


4 Responses to

  1. John Page says:

    I enjoyed working through your affiliation data webpage at

    Don’t you also have to redo “V(magallg)$degree = degree(magallg)” for magallggt1 in order to get the final graph? I didn’t see that line included.


  2. Richard Rice says:

    Hi Solomon,
    I have 2 questions:
    1. Will Data Analysis discuss Bayes theorem?
    2. This second question is a little longer. First some background. I
    collect weed species data in the field for the Washington state dept
    of natural resources(DNR). There are several Android apps for
    identifying weeds by looking at photos but none that I can find by
    comparing a photo that I take with my Android phone with a
    downloadable database of known weed species. What I’d like to do is
    write an app that downloads DNR’s weed photos of which there are about
    1200 to my phone, find a weed in the field, take a photo and compare
    it with DNR’s photos to see if there is a match.
    Does this sound feasible? I want to keep it simple, not try to
    identify every weed in existence, just here in Washington.

    Best Regards,


    PS: I tried going through the Discussion Forum but didn’t get a response.

    • Solomon says:

      Hi Richard, I’m not sure what you’re referring to the first part of your question, but for your second, take a look at caffe ( which provides some libraries to train image classifiers. What you’re proposing sounds like it will require a large set of images for training so I’d recommend thinking about incorporating crowd-sourcing to come up with a large and reliable training set.

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s