more tweets, more votes: in foreign policy, PLoS One, and hitting the top 10 list

More Tweets, More Votes news:

  1. I thank Alex Hanna for mentioning this work in a new Foreign Policy piece that discusses how social media can be used to monitor elections in nations where polling is rare, a possibility that I mentioned in my Washington Post article on MTMV. Alex and co-author Kevin Harris use social media data to track Iranian public opinion, because quality polling is not common there. A must read for people who want to see how social media can be used to measure and evaluate democratic processes.
  2. The peer reviewed version of MTMV is now out in PLoS One. The paper presents the tweet share/vote share correlation for the 2010 and 2012 House elections and discusses possible mechanisms.
  3. The working paper version of MTMV at Social Science Research Network has had over 1,200 downloads in its short life, pushing it into the top 10 most downloaded papers on models of elections and political processes at SSRN. Congratulations to my co-authors Joe DiGrazia, Karissa McKelvey, and Johan Bollen. Outstanding work.

Insider tip: New results be presented at the computational social science workshop at the University of Chicago in January 2014. Details forthcoming.

These books cure baldness: From Black Power/Grad Skool Rulz

Written by fabiorojas

December 16, 2013 at 12:01 am

One Response

Subscribe to comments with RSS.

  1. Hi Fabio, long-time reader, first-time commenter. I finally read your thoughtful article on social media as an indicator of political behavior. I think it’s a nice contribution to the field, particularly by showing a way around the minefield of sentiment analysis when working with social media data. I also read the Q&A you posted after presenting the paper at ASA.

    I didn’t read it in detail or chime in earlier as I was knee-deep in the academic quarter.

    I wonder if what we’re really seeing in the data is “political behavior” in the sense you meant it to be. Are you sure it isn’t professional behavior? I strongly suspect it is. If so, your claim — that social media data holds “useful information” — is still mostly true, but for different reasons.

    Suppose what you’ve seen is not political behavior but an extension of the media circus. Social media data about politics, I would hypothesize, grants access to the minds of a broader and more heterodox subset of the chattering class than CNN does. But it is still a subset of the chattering class — activists as well as politics professionals like journalists, consultants, and political operatives — and not representative of an “average voter.”

    As has already been pointed out, it’s very hard to accurately locate the geographic origin of tweets, since tweets are not geocoded and users use their “location” field for irony as often as they do for conveyance of factually accurate information. In this study, you don’t even try to geolocate tweets, which is smart. You also concede that you may have been working with tweets generated by robots and nonvoters instead of tweets generated by in-district voters. In fact, that’s a near certainty. And we know from a variety of sources that activists and people who are already highly partisan are more likely to tweet about politics than other kinds of people.

    Just the same, you say, the candidate who gets tweeted about the most is very often the candidate who wins, even when controlling for CNN mentions or incumbency. Why? A theory that could be tested empirically is that the users you are dealing with here are primarily activists, politics professionals, and their robot minions. In that case what you are doing when looking at tweets is not looking at the “political behavior” of some ideal voter or citizen. Instead you are looking at the “political behavior” of the vanguards of various candidate committees and causes. It is probably true, not to mention interesting, that winners often attract more activist activity than losers. I agree that this is useful information — I’m just not sure my reasons are your reasons.


    Nick Judd

    January 2, 2014 at 5:59 pm

Comments are closed.

%d bloggers like this: