Slashdot Mirror
Examining Presidential Candidates Via Google Trends
Michael Giuffrida writes "Google Trends is a free application produced by Google that shows how often a given keyword is searched for, over time. After seeing how candidates in the 2008 primaries have done in Google Trends in different states, it's clear that this tool can be very useful for campaigns." Read on below for some of the specifics about how these candidates have fared, Google-wise.
"For example, in New Hampshire, in the days leading up to the Jan. 8 primary, Clinton was searched for the most, followed by Obama, followed by Edwards — which was how the primary results turned out. In other words, the candidates most searched for on Google by users in New Hampshire were also the candidates with the most number of votes. This works for many other states as well.
For the first 37 Democratic primaries and caucuses, 32 states had enough data on Google to make a prediction. This method correctly predicted 27 of those 32 sates. Predictions aside, the tool is also useful simply in finding out how popular a candidate is in different states, assuming that the more popular candidates are entered more often as a search term in Google (an assumption that was verified, at least for the Democratic primaries, by the positive association found)."
For the first 37 Democratic primaries and caucuses, 32 states had enough data on Google to make a prediction. This method correctly predicted 27 of those 32 sates. Predictions aside, the tool is also useful simply in finding out how popular a candidate is in different states, assuming that the more popular candidates are entered more often as a search term in Google (an assumption that was verified, at least for the Democratic primaries, by the positive association found)."
Sir, every time you mention bird rights and protection your page rank seams to rocket.
IranAir Flight 655 never forget!
Interesting, but I don't think it's that hard to beat an 84% accuracy rate with traditional methods.
[Fuck Beta]
o0t!
...without actually RTFA:
"For the Republican Primaries, last names could easily be used. Ron Paul was excluded. His last name is too common. Using his full name is not a good solution either, because he had massive popularity on the Internet, becoming a meme of sorts, which did not at all correspond with his actual successes (or lack thereof) in the primaries."
It seems their method does rather poorly when looking at republican primaries. Overall, they comment: "In reality, only about half of the "predictions" before the 2/12 primaries were actually accurate. "
Still, one would expect logically that interest in a candidate is related to their poll numbers. But you need a better way to distinguish between negative interest and positive interest: how many people are searching "Obama AND Wright video" vs "Obama AND race speech"? With a more detailed model they could be on to something.
I came here for a good argument
The sample: folks on the internet.
Who's missing: folks who aren't on the internet; like old farts, poor people and Amish. As far as the old farts are concerned: they are the most well organized and the most vocal political group in this country. I think these charts reflect nothing.
There are still a lot of people without computers/internet/education that won't be using Google, thus you could seriously under-represent the base of a particular candidate. Dewey defeat Truman, anyone?
The author is quick to dismiss using "Obama" and "Hilary" as the indicator terms for fear that Obama's huge online campaign popularity is not representative of the true popularity of the two candiates.
However, he makes no mention of the fact that "Obama" and "Hillary" are the most popularly used terms to refer to the candidates. Almost all candidates are refferred to primarily by their last names. Hilary is a special case where we use her first name because her husband was so recently president.
His use of "Barack" and "Hilary" is about as statistically accurate as using "Barack" and "Rodham". Fortunatly, this inaccuracy is obviously visible in his numbers, because using his first-name method it quickly looks like Edwards might be a write-in candidate to rival them both.
Please slashdot, stop posting braindead stories.
So, in other words, any data that contradicts the hypothesis will be thrown out.
Slashdot: Playing Favorites Since 1997
Hey, guys, You're all right. There are serious statistical flaws here. I chose the keywords "hillary" and "barack" and "edwards" because that was the model that showed the best success. If one were actually predicting this live, he or she would soon see that "hillary" and "barack" do produce better results and would switch to those terms, simply because it fits the model better. Every election will have its outliers (Obama, Ron Paul). But hopefully this brief overview will provoke some campaign analysts to actually try to interpret Google Trends results for themselves, using more advanced models.
Good thing someone did compare Ron Paul to everyone else in Google Trends: http://www.youtube.com/watch?v=7iW5kOB1pmg
Why include Giuliani and Thompson and not Ron Paul? I would rather see Ron Paul than those other two who Ron Paul consistently beat. He was kicking butt in terms of Google searches.
Does this mean that the next President of the United States will be Tila Tequila?
I've calculated my velocity with such exquisite precision that I have no idea where I am.
i've been using google trends for several years to see what information people really need as they go about their daily lives.
Global Warming vs. Paris Hilton
Global Warming vs. Iraq
(ignore the bottom chart, it is irrelevant to my study)
in this age of communication i'm just not getting through
Dark Reflection
Because it's easy to predict the past via cherry picking. It's hard, if not impossible, to predict the future.