Follow Slashdot blog updates by subscribing to our blog RSS feed

 


Forgot your password?
Close
typodupeerror
×
Social Networks Stats Twitter Politics

Twitter Buzz As an Election Predictor 55

Posted by Unknown Lamer from the popularity-contest dept.
Capt.Albatross writes "A study presented at the American Sociological Association's annual meeting suggests that simply comparing the frequency with which the candidates' names are mentioned in tweets can predict the result of elections almost as well as conventional polls, even without considering the sentiment (for or against the named candidate) of the messages. Furthermore, the correlation seems strongest in close elections. Additional commentary can be found at the Wall Street Journal and from Indiana University."
This discussion has been archived. No new comments can be posted.

Twitter Buzz As an Election Predictor More

Twitter Buzz As an Election Predictor

Comments Filter:

  • Most of those are bots. (Score:5, Insightful)

    by stewsters ( 1406737 ) on Wednesday August 14, 2013 @10:25AM (#44564487)
    Google "buy twitter followers" and you will see a lot of companies dealing with this. Most of the time when you get random followers who just tweet the same format of things, its because they are bots.

    Whichever candidate can afford hire the most companies to have bots repost what they are tweeting have the highest chance of winning. It all comes down to who has the most money for advertising, same as always.

    • Google "buy twitter followers" and you will see a lot of companies dealing with this.

      The WSJ article mentions 'promoted' tweets as well as tweets from the candidates' organizations, and says the researchers found that they tended to cancel out (this also suggests they were not being excluded from the study.) This study might provoke attempts to game future measurements, but fortunately, this is only about prediction, not actual voting (unless correlation actually does imply causation in this case, but there is no suggestion that it does.)

    • Re: (Score:2)

      by umghhh ( 965931 )
      now replace the other side i.e. politicians with bots and the whole system may even start working efficiently.

    • Speaking of bots... I'd like to propose a new flying hunter-killer robot that tracks down people who submit election-related news when there is no election happening in the next month . By all means, go bat-shit crazy about the election when it's actually timely... but right now, nobody gives a fuck. No really: The number of fucks given counter hit zero almost a year ago. The care-o-meter in Carealot is pointing straight down. Tenderheart is cutting his own wrists right now and sobbing. Grumpybear finally

      • Re: (Score:2)

        by mcgrew ( 92797 ) *

        even rabid christians and retailers hoping for some dollars for jesus

        Firstly, Christians aren't clamoring for a longer Christmas season. Most Christians I know complain about how long it is. Secondly, retailers don't give two shits about Jesus, they worship money. Their holiday, when they worship THEIR god, is called "Black Friday".

  • Limitations (Score:3, Insightful)

    by kubajz ( 964091 ) on Wednesday August 14, 2013 @10:26AM (#44564501)
    Yes, perhaps a good predictor now, but only up to the moment when results of these polls are widely publicized... and some company offers to manipulate the trending words for a price?

    • and some company offers to manipulate the trending words for a price?

      Would there really be a market for manipulating an opinion poll? Having the measure of people's voting rigged won't change the election.

      If there is a market for this then maybe there's a market for selling rigged weighing scales to fat people so that the scales say they've lost a pound every time they weigh themselves.

      • Would there really be a market for manipulating an opinion poll?

        Yes. There are more than enough people in the world who do things because "everyone who is anyone is doing it".

        • Would there really be a market for manipulating an opinion poll?

          Yes. There are more than enough people in the world who do things because "everyone who is anyone is doing it".

          True, but in other circumstances, such as a race that is polling as unexpectedly close, it might provoke more supporters of the underdog to vote. I am certain that the questions of how to game the predictions, when, and in which direction, are being actively studied.

          It should be noted that in the last U.S. presidential election, partisan predictions did not seem to affect the result, and Nate Silver became famous for accurately calling it by being as objective as he could.

  • Mind you, this is cheap way of astro-turfing [wikipedia.org]. But beyond the most superficial analysis, astro-turfing fails quickly. especially where reputation is considered. Create a couple of thousand of twitter bots ? Easy. Getting real people to follow them ? Hard. . .

  • Likely a "Red Herring" so to speak. (Score:1)

    by Anonymous Coward

    My wife worked for an online "Marketing Sentiment" company, and she came up with the idea of trying to predict the American Idol winners using a very similar technique about 4-5 years ago (I forget exactly).

    She found that it showed increased "excitement" in general terms, and generally there was a correlation with increased voting on American Idol, but it did not accurately predict the specific winners each week.

    It sometimes seemed to work, though, so she (and others) messed with the algorithm quite a bit a

  • Really? (Score:3)

    by mmcxii ( 1707574 ) on Wednesday August 14, 2013 @10:38AM (#44564629)
    How's that Twitter thing working out for Anthony Weiner?
  • ...we can vote in elections via Twitter.
  • following events on Twitter is a blast. I did not watch the presidential debates, I just followed the twitter hash-tag. It is like watching a movie audience where you can see the film or even hear it, you just have to judge what is happening by the audience's reaction. It is much more revealing than you would imagine. For example, you can see who is going to win the debate 15 minutes into the debate. The dynamic is established that quickly. And there are surprises. For example, when "binders full of women"
  • successful twitter campaigns will increase voter turnout in the voting polls (for both parties). the voting booths and locations will not be equipped well enough to handle the normal volume of voter turnout because most of the sheeple are used to staying home rather than actually taking the time to vote. they'll show up and thousands of democrats will find that they should have registered to vote but didn't and so now they cant, or else they will have registered but some republican somewhere in the chain of

  • The pretext makes for good media fodder, so it's hard to judge the plausibility of the results without looking at the actual study. Couldn't find it in the Washington Post article or through a quick search. A few questions that come to mind..

    - How many elections were studied? If it's a small number, then are the models overtrained? It's easy to come up with a model that connects two data sets if the data sets are known !
    - Are "negative" tweets distinguished from positive ones in some way? If people dislike

  • Just great... Cue tens of thousands of paid campaign staff trying to boost their candidate's stats.

  • Maybe if things were transparent.. (Score:3)

    by brxndxn ( 461473 ) on Wednesday August 14, 2013 @11:16AM (#44564971)

    In the 2008 election, there was an enormous interest in Ron Paul. His google searches were higher than any other Republican nominee for most of 2007 and 2008. His Twitter interest was huge.. http://www.nethosting.com/buzz/blog/ron-paul-wins-gop-nomination-if-twitter-votes-counted/ [nethosting.com]

    But, things are not transparent like that in the US. The mainstream media controlled the 'buzz' around Ron Paul and continued to act like he had little chance. The google trends and Twitter followers were ignored. The Internet buzz was discounted.

    Maybe this article will be accurate in the future as the Internet takes over (and more so the Internet Generation takes over).. But if you tried to predict the last election based on Twitter, you would either be thinking there was massive fraud or there somehow was a huge amount of the US population that never heard of the Internet.

    • I am not sure I want the media to waste more time reporting on random crap on twitter. The few times I have watched TV news they like to spew lots of crap from their twitter feed up there now. It would be nice if they just went to the facts instead.

      Your points on ignoring Paul during the GOP primaries was well noted. I noticed the same thing such as the radio news would mention every other candidate but him and would never report on percentages he got while mentioning every other candidate. At least if Pa

    • Nobody voted for Ron Paul because he wasn't expected to have a real chance at getting elected. Instead of voting for a losing proposition, most people voted against the republican or democrat that they didn't want to win.

    • The mainstream media controlled the 'buzz' around Ron Paul and continued to act like he had little chance.

      They "acted like he had little chance" because he actually had no chance of winning. In 2012, Ron Paul had tons of mainstream media exposure. The more the general public found out about him and his policies, the worse his poll numbers got.

    • But if you tried to predict the last election based on Twitter, you would either be thinking there was massive fraud or there somehow was a huge amount of the US population that never heard of the Internet.

      In the 2012 election there WAS enormous fraud in the Republican primary/caucus process, most of it perpetrated by Romney's supporters against Ron Paul's. Some of it was violent. Much of it was transparent.

      You don't hear about it in the mainstream media, left and right, which was blacking out anything re

  • It seems that now that this has been observed, outcomes are bound to change.

  • that a large enough population of people who vote will actually say who they vote for given the chance and that result reflects reality.

    • that a large enough population of people who vote will actually say who they vote for given the chance and that result reflects reality.

      Last year I kept track of the Facebook Likes over time for our State gubernatorial primary candidates, and used both the final Like-count and the momentum to make a prediction:

      http://www.billmcgonigle.com/can-facebook-predict-the-nh-primary/ [billmcgonigle.com]

      The actual vote was very close to prediction, especially considering the 'intelligencia' was predicting a very close race with opposite

      • Re: (Score:2)

        by gelfling ( 6534 )

        Well sure - it's basically casting your polling net as wide as it can go and not filtering for any preconceived anything and not tossing out perceived outliers.

  • Not a single graph on any of those links...

  • God bless you, Washington Post. [washingtonpost.com]

    They actually went to the trouble of including a damn chart [washingtonpost.com], which shows just how weak the correlation actually is.

    • Yes it is a very weak correlation but it appears more asymptotic instead of linear to me anyway. Man I need to start gaming the system so I can be a presidential contender the next time around.

  • Umm, no offense to our friends at Gallup and such, but shouldn't we set the bar a little higher?

  • ...because the moment something like this is identified, it will be gamed.

  • Ok, here's the thing. If Twitter use/mentions currently are a good predictor of election results, then that's cool. However, when you make it known, you invite a bunch of intentional skewers to the mix thus destroying the instrument.

  • in an inverted fashion from how Nate Silver surfaced way back in 08 that under-representing cell-phone-only voters in polls under- represented the young, it'd seem that using twitter as a representative sampling will under-represent the old - e.g. those who vote more than the young do? http://fivethirtyeight.blogs.nytimes.com/2012/09/19/obamas-lead-looks-stronger-in-polls-that-include-cellphones/?_r=0 [nytimes.com]
  • Need any more proof your elections are rigged ?

Slashdot Top Deals

E = MC ** 2 +- 3db

Close