Google's PageRank Predicts Nobel Prize Winners 101
KentuckyFC writes "The pattern of citations between scientific papers forms a network that has remarkable similarities to the network formed by the web. So why not use Google's PageRank, the world's most effective search algorithm to rank these papers in the same way it ranks websites? That's exactly what a couple of US researchers have done for physics papers published by the American Physical Society since 1893 (abstract). The results make interesting reading because almost all of the top ten papers resulted in (or were linked to) Nobel Prizes for their authors. Which means that studying the up-and-coming entries on the list ought to be a good way of predicting future winners. Better get your bets in before the bookies get wind of this."
Great, Just Great (Score:2, Funny)
Re: (Score:2)
You say this, and I imagine a Cessna Citation business jet armed with comically large bombs that it drops on scientists houses.
Re: (Score:1)
Re: (Score:2)
Of course, in the application of PageRank to general internet search, there is a clear economic incentive to game the system (and so sometimes you see it done).
Why would anyone care enough where they land in a PageRank search of academic papers to game the system?
Re: (Score:1)
Re: (Score:2)
Re: (Score:2)
Re: (Score:2)
When a search is performed for whatever the modern equivalent of radiation and x-ray crystallography* is, that person's paper would then pop up first, garner more citations, and potentially end up an authoritative source on the topic.
*Take a look at the contributions of early Nobel winners in Physics.
Re: (Score:1)
>That's exactly what a couple of US researchers have done for physics papers published by the American Physical Society since 1893 I wasn't aware that Google's PageRank existed in 1893.
It didn't. But they don't just throw away published papers. Those papers tend to sit around on a dusty shelf, forgotten in a library (unless they're really well-cited). Or in an archive (most likely).
Re: (Score:1)
Re: (Score:1)
bets? (Score:1)
Re: (Score:1)
Sure, 20000000000000000:1 odds for myself, in economics, in the next 40 years.
Re:bets? (Score:5, Informative)
They take bets about this kind of thing?
Um, yeah, you would be surprised what offshore betting brings to the internet. My friend had money that Obama would say "Always bet on black" for his opening speech (paid 700:1) and that he would use the word 'banana' in his speech (paid 800:1). He lost them both. He also bets on every play during football games, especially returns. And he also bets on how long the national anthem lasts at the beginning of each game.
I wish I could link you to the site but it's hard to get to.
You may be able to say that there is always someone willing to quote you a line for anything anytime as long as they get a cut/rake.
Re: (Score:3, Funny)
Can I propose a simpler scheme where your friend just mails me money while being a racist nitwit? As long as that's his idea of a hobby...
Re:bets? (Score:4, Interesting)
Can I propose a simpler scheme where your friend just mails me money while being a racist nitwit? As long as that's his idea of a hobby...
Sure, as long as you are willing to send him back several thousand dollars in the event of some highly unlikely event. It's called "gambling" and he loves the it. He's also Indian American and has a great sense of humor.
Perhaps your "racism" comments would be more better directed at the Irish bookie making these offerings to the betting community [speroforum.com]? I think the "Obama Cliche Betting" section has most of what was being offered.
Re: (Score:2)
What will happen first under President Obama?
4/6 American led signed cease-fire agreement between Israel & Hamas
3/1 Full Troop withdrawal from Iraq
8/1 Capture of Osama Bin Laden
8/1 Online Gambling legalised
10/1 Full National recognition of Same Sex Marriage
12/1 Full Troop withdrawal from Afghanistan
18/1 Legalisation of Marijuana
20/1 Constitution changed to allow the President to serve 3 or more full terms
25/1 Total ban of Capital Punishment
50/1 Moonwalk confirmed as a fake by Obama
100/1 Complete ban on privately owned guns
500/1 Discovery of Aliens on Mars
FUUUCK, your friend is gonna be sooo rich. We already found ice on Mars!
Re: (Score:2)
The part that bothers me is that the moonwalk being a fake is considered 10 times as likely as life on Mars.
Re: (Score:1)
And you write like a coward. Why don't you read the link he provided [speroforum.com]?
Re: (Score:3, Funny)
"If someone gives you 10,000 to 1 on anything, you take it. If John Mellencamp ever wins an Oscar, I am going to be a very rich dude." ~ Kevin, The Office
movie-star (Score:5, Insightful)
Did the star make the movie a hit, or did the movie make the star?
For 'prediction' to be valuable, it has to work with citations that were linked *before* the paper got the Nobel.
Nicola Cabibbo (Score:2, Interesting)
So even in this article Nicola Cabibbo demonstrated to deserve the Nobel Prize:
http://en.wikipedia.org/wiki/Nicola_Cabibbo [wikipedia.org]
Re: (Score:2, Interesting)
I hope they never award the Nobel Prized based strictly on this. It could be a good way of pointing people in the right direction, but it will also let in a bunch of crap.
The last thing we need is scientists Googlebombing their papers (or creating junk networks to increase page ranks). I bet the Creationists would have a field day with this. "Look, our theories have scientific basis, check out our CiteRank".
Technology is a tool, it should never replace human intelligence.
Re: (Score:1)
However, give the tech and networks behind such algorithms twenty years or so, and you'll probably find that human beings are no longer the most intelligent species on the planet.
Re: (Score:2)
Weather is the odd one out because all the other variables are influenced by the prediction made. Expectations of risk (or correlation of currency movements, or default rates on loans) affect the
Re: (Score:2)
There's nothing wrong with computer models, without them we'd never get any high end engineering done.
However the model can't be better then it's underlying assumptions and here I think that they've confused the relationship.
Re: (Score:1)
Are your crazy? The only way we're doing weather prediction is with computers. Its amazing how accurate we can get. It may not be up to the standards you have imagined in your brain, but here in the real world its pretty good considering.
computer models have failed to accurately manage loan portfolios to higher risk buyers
Garbage in, garbage out. If the algorithm is written in way that makes the same assumptions the bankers made (packing high risk nightmare loans with low risk loans == win) then you will ge
Re: (Score:1)
Let's see, so far, computer models have failed to accurately manage loan portfolios to higher risk buyers, failed to manage risk books for hedge funds, could not capture currency trading, can't predict the weather and are probably wrong about climate. Sure, let's have them predict nobel prize winners while we are at it!
Actually, using it to predict Nobel prize winners would be a silly use.
But it would be quite useful to allow scientists to focus their research, find all the tidbits, maybe shed some small extra bit that they may have missed otherwise.
Re: (Score:3, Interesting)
Let's see, so far, computer models *can* predict the weather and are probably *right* about climate.
But unsurprisingly have failed to accurately manage loan portfolios to higher risk buyers, failed to manage risk books for hedge funds, could not capture currency trading, simply because they are not predictable because they are traded by panic driven, idiots who are swayed by rumour, non existent trends, and computer predictions!
The predictable but complex is predictable, the unpredictable ... is unpredicta
Re: (Score:2)
panic driven, idiots who are swayed by rumour, non existent trends, and computer predictions!
Sounds like we should be using Macs to predict the economy -- that's their main source of operating power anyway :-p
Re: (Score:2)
Let's see, so far, computer models *can* predict the weather and are probably *right* about climate
The reason I made the crack about the Climate was because the reason some of the long since resolved Mann controversy was because he used code that he also used for banking and thus couldn't share it. I don't remember the exact deal or even if it was true, but the thought inspired me to a joke, if it were true.
So, if you can put aside your feelings about gw for a second, given that the left has so much riding
Re: (Score:1)
Let's see, so far, computer models have failed to accurately manage loan portfolios to higher risk buyers, failed to manage risk books for hedge funds, could not capture currency trading, can't predict the weather and are probably wrong about climate. Sure, let's have them predict nobel prize winners while we are at it!
Well, it's certainly easier than trolling Nostradamus' quatrains in search of a prediction, now isn't it? ;)
Or: International fame = more hits to your paper (Score:5, Insightful)
Seriously, like this is some kind of weird correlation. No shit Nobel prize winning papers would have excellent page ranks.
Re: (Score:1)
So novel and useful research is at the hub of a web of citations, and the novel and useful web pages are at the hub of a web of links ....
Wisdom of Crowds != Wisdom of Intellectuals (Score:1)
Google PageRank = Wisdom of Crowds
And Wisdom of Crowds != Wisdom of Intellectuals
When they think we know, they change their mind (Score:1)
Yes, it happens all the time: the Swedish Academy can change their vote any time, if it feels pressed by the media.
Wrong assumptions (Score:1)
Unless... (Score:1)
That's true, unless this algorithm only searches through papers linked before the cooresponding announcement--which is what my first thought was on seeing the sumamry. I did not RTFA, though.
Take with a bucketful of salt (Score:2)
The original paper doesn't really discuss the connections with Nobel prizes - it mentions as an aside that one paper was cited for a Nobel prize - as it's concerned not with predicted Nobel laureates but evaluating the importance of papers. Therefore any conclusions about predicting Nobel winners are without merit until further analysis is performed.
Pft.. that'd be easy to do. Pick something harder (Score:2)
Bowel movements would be pretty easy to predict tbh. You just get the Android app to track your bowel movements, it'll upload it to a google appliance gizmo that creates a trend.. maybe some input function to add in the primary sections of your diet (for instance, you ate something with alittle more fat or fiber.. etc..)
MS-BM 2.0 (Score:1)
See, what did I tell ya? Google lets their employees work a bit on odd experiments, and this is the kind of thing it may lead to. (Will Microsoft compete with Microsoft Bowel 2.0 ?)
Re: (Score:1)
Re: (Score:2)
If I eat at Baja Surf, predict bowel movement within 5 minutes of leaving restaurant?
Google Page rank and most frequent searches is Au (Score:1)
Re: (Score:1)
That was my reaction as well. It only works if you base it on publications prior to them winning the Nobel Prize. Of course people are going to reference the papers after the Prize. Citing a Nobel winner gives a certain boost to credibility.
Re: (Score:2)
No Kidding (Score:5, Informative)
The algorithm for Google PageRank is based on the concept of citations from academia. If I remember correctly, the software was originally meant only to index academic papers and eventually grew to index the whole internet. So its not surprising that it predicts winners so well (depending on how much the Nobel committee weights citations in their decisions).
Re: (Score:2)
Re: (Score:2)
I don't know how one is nominated for a Nobel, but I don't think the decision takes citations into account at all. However, influential works are both more likely to win a Nobel prize and more likely to be cited often.
PageRank is very much like academic citation.
Re:No Kidding (Score:5, Informative)
The algorithm for Google PageRank is based on the concept of citations from academia
Exactly!
Quoting from the original paper: "It is obvious to try to apply standard citation analysis techniques to the web's hypertextual citation structure. One can simply think of every link as being like an academic citation. So, a major page like http: www.yahoo.com will have tens of housands of backlinks or citations pointing to it" [L Page, S Brin, R Motwani, T Winograd. The pagerank citation ranking: Bringing order to the web ].
the software was originally meant only to index academic papers
That's not right. From the same original paper:
"PageRank is a global ranking of all web pages, regardless of their content, based solely on their location in the Web's graph structure "
Anyway you are right, and the article's idea sounds way too old: probably an example of two research communities (physics & citation analysis) not knowing too much of each other
Re: (Score:1)
not the interweb (Score:2)
Note that they're not looking at webpage referrals, but citations in other scientific papers. Rather than simply counting citations, they're weighting the citations by the number of citations the citing papers received. Thus, if your paper is cited by a paper which is very popular, then your paper will get a boost to it's citation score.
winners bias? (Score:5, Insightful)
Not having read the actual paper, the following question comes to mind: did they include only the period of time *before* the physicists got their Nobels? Because if they included the citations after that - yeah, I imagine those authors got quite a few citations being Nobel Prize winners and all...
Re: (Score:2)
Yeah, I thought the same thing. Then I actually read the article. They aren't claiming the highest ranked pages are going to win a Nobel. In fact the author of the highest ranked paper has not received a Nobel. Instead they are suggesting that authors of higher ranked papers are likely candidates for a Nobel. If they had done what you suggest, it would have been more interesting.
Re: (Score:2, Informative)
In other news... (Score:5, Insightful)
Top 40 music singles chart predicts highest-selling singles of the week with astounding precision!
Logical Progression (Score:2, Funny)
The next step is obviously to let PageRank select the Nobel winners and cut out the middleman.
Re: (Score:2)
The next step is obviously to let PageRank select the Nobel winners and cut out the middleman.
I can't wait for my first Nobel Prize Optimization spam.
Re: (Score:1)
So Tired of Useless Tags (Score:5, Insightful)
Re: (Score:2)
Check out "The Case of El Naschie" for how to game academic publishing. (Become an editor of a vanity paper, publish 5 articles a month, cross-cite every article with 10 similar 'scientists').
Re: (Score:2)
Lets tag this article with "lametags" or "uselesstagsincludingthisone" =P
hmm indeed (Score:2)
And of course the results of their experiment are submitted in the form of a research paper. Hmm, I wonder...
Re: (Score:1)
It talks about prediction ... for ... which correlation is enough.
If it rains, I'll stay indoors. Therefore, if I stay indoors, it'll rain!
Winner bias (Score:1)
This would be quite obvious, but then again what is Google for anyway?
---
Have you read the Terms of Service [sourceforge.com] lately?
I am shocked! (Score:1)
You mean people who write good papers get Nobel prizes? Wow!
Also, I didn't know that people who won Nobel prizes for fundamental discoveries won't post facto get gratuitous citations in the first line of the introduction of every subsequent paper in the field.
Page Rank captures whatever is `sensational', in every domain of human activity. Having RTFA, I conclude that if all that is sensational is good, then what we have here is an empirical demonstration of circular reasoning. If all that is good need
Large Numbers (Score:2)
The foundation for the work of Messrs. Maslov and Redner was laid by Hari Seldon, who discovered [wikipedia.org] that "while one cannot foresee the actions of a particular individual, the laws of statistics as applied to large groups of people could predict the general flow of future events." The recent paper by Messrs. Maslov and Redner represents the smallest corpus to which Seldon's theory has been successfully applied to date.
Further applications of these techniques to this same corpus will likely fall afoul of Seldon
Re: (Score:1)
Yeah, Hari Seldon [wikipedia.org]'s work lays an interesting Foundation [wikipedia.org] for Psychohistory [wikipedia.org].
Citations are often negative (Score:4, Informative)
Cause and effect confusion (Score:2)
Impact factor? (Score:2)
I wonder how different the result are from the normal cumulated Impact factor of the scientists publications....
But i forgot. Google is the only database on the planet....
popular != important (Score:1)
Cause or Effect? (Score:2)
backwards history (Score:2)
Actually, citation ranking was first and developed some time in the 1970's. Google's page rank algorithm was an application of citation ranking to the web. The original Page Rank paper even cites the citation ranking papers.
(This also kinds of points out a problem with citation ranking: everybody these days is going to cite page rank, even though the idea originally was developed by other people. So, citation ranking isn't going to tell you who should get the credit, only who popularized an idea.)