Twitter Buzz As an Election Predictor 55
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."
Isn't it kind of Dada? (Score:3)
Re: (Score:1)
Re: (Score:3)
Correlation does not imply causation.
But in this case, correlation can lead to causation.
1. Send lots of tweets to simulate popularity.
2. Get publicity for being "in the lead".
3. Get more attention from journalists, debate organizers, and potential voters.
4. Get donations from special interests that want to back a "winner".
5. Profit!
Re: (Score:3)
Correlation does not imply causation.
Obligatory http://xkcd.com/552/ [xkcd.com]
Re: (Score:1)
Re: (Score:2)
And...Twitter being the sole domain of the Narcissists, I don't think it is anywhere near a representative sample of the voting population.
Re: (Score:2)
Considering that 45% of Americans under age 35 turn out to vote and 70% of people over 65 vote, there is a high likelihood that a person tweeting about a candidate *isn't* going to vote for that person. And that the people that are going to vote have never seen Twitter before.
Most of those are bots. (Score:5, Insightful)
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.
Re: (Score:2)
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)
Re: (Score:3)
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)
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)
Re: (Score:2)
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.
Re: (Score:2)
Yes. There are more than enough people in the world who do things because "everyone who is anyone is doing it".
Re: (Score:2)
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.
Because Spam = Reality ??? (Score:3)
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)
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)
Talk to me when... (Score:2)
on the other hand (Score:2)
i can totally see this happening (Score:1)
Link to the study? (Score:1)
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
Here come the paid DRONES (Score:2)
Just great... Cue tens of thousands of paid campaign staff trying to boost their candidate's stats.
Interesting Twitter Graph (Aussie Election) (Score:2)
http://votecompass.com/images/au-2013/auspol-twitterverse.jpg [votecompass.com]
Maybe if things were transparent.. (Score:3)
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.
Re: (Score:2)
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
Re: (Score:2)
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.
Re: (Score:2)
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.
Re: (Score:2)
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
What would Schrödinger have to say about this (Score:2)
It seems that now that this has been observed, outcomes are bound to change.
Gee who knew (Score:2)
that a large enough population of people who vote will actually say who they vote for given the chance and that result reflects reality.
Re: (Score:2)
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)
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.
There is (Score:1)
Picture's worth a thousand words (Score:2)
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.
Re: (Score:2)
"almost as well as convention polls" (Score:2)
Umm, no offense to our friends at Gallup and such, but shouldn't we set the bar a little higher?
Once it's reported, it's no longer valuable (Score:2)
...because the moment something like this is identified, it will be gamed.
Once you advertise it, you ruin it... (Score:2)
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.
twitter under-represents the old ? (Score:1)
Huh uh (Score:1)