Twitter’s mood predicts the stock market?

Paul Raven @ 20-10-2010

I can’t really reword this one to sound any less (or more) incredible, so I’m gonna go straight to quotes:

The emotional roller coaster captured on Twitter can predict the ups and downs of the stock market, a new study finds. Measuring how calm the Twitterverse is on a given day can foretell the direction of changes to the Dow Jones Industrial Average three days later with an accuracy of 86.7 percent.

“We were pretty astonished that this actually worked,” said computational social scientist Johan Bollen of Indiana University-Bloomington.

You and me both, Johan, you and me both… but then, it’s a weird old interconnected world we live in, isn’t it?

“We’re using Twitter like a psychiatric patient,” Bollen said. “This allows us to measure the mood of the public over these six different mood states.”

As a sanity check, the researchers looked at the public mood on some easily-predictable days, like Election Day 2008 and Thanksgiving. The results were as expected: Twitter was anxious the day before the election, and much calmer, happier and kinder on Election Day itself, though all returned to normal by Nov. 5. On Thanksgiving, Twitter’s “Happy” score spiked.

Then, just to see what would happen, Mao compared the national mood to the Dow Jones Industrial Average. She found that one emotion, calmness, lined up surprisingly well with the rises and falls of the stock market — but three or four days in advance.

As daft as it sounds on the surface, this is probably pointing at some sort of core truth; it’s pretty much established that markets are emergent systems born of human interaction, so why shouldn’t you be able to get an idea of where things are going by finding a way to sample the mood of the planet?

That said, I’d very much like to know how wide-ranging the Twitter sampling was: did they use multiple languages, for instance, or just English? I suspect that Twitter’s demographic in geographical terms is still very white, Western, male and middle-class, too; would these results be strengthened by using more data from wider sources, or has a sort of accidental cherry-pick taken place? (White Western middle-class males are more likely to be stock owners or investors of one stripe or another, I’m guessing, so there’s probably some sort of inherent bias in using Twitter as a sample source.)

Even so, I’m fascinated by research that treats human civilisation as a system-of-systems with observable properties, and the rise of social networking is probably the catalyst for this growing field. Whether knowing how the system reacts and correlates will allow us to control it more effectively is another question entirely, of course… feedback is a powerful thing, but as any guitarist will tell you, it comes with risks. 😉


The Iranian elections: is democracy viral?

Paul Raven @ 15-06-2009

Iranian election protestorsThe past weekend’s hot news story is still smouldering strongly today: the Iranian elections (and the resulting landslide victory for incumbent president Ahmadinejad) have resulted in accusations of vote fraud (which isn’t entirely surprising) and street riots and protests from supporters of the principle opposition candidate, Mir Hossein Mousavi. Throw in some state censorship in the form of social networking websites and text messaging services being blocked, and you’ve got a story that’s not entirely unfamiliar in recent years. [image by Shahram Sharif]

Of course, I have no idea whether or not the election was rigged or not, though I have my suspicions. What interests me most about this story is how it paints a very different picture of Iran to the one we’ve been fed in the last decade or so. Far from being a monolithic Islamic state in thrall to Ahmadinejad, there’s evidently enough support for reform to threaten the incumbents; after all, a mere handful of angry reformists does not a riot (or an electoral recount) make.

How long this has been the case is beyond my knowledge, and I wish I had the time and opportunity to research it further. But the ubiquitous presence of peer-to-peer communications (and their inevitable censorship by the state) is telling, and I find myself wondering if perhaps the talk about democracy being a viral concept has some weight to it after all. Have services like Twitter and Facebook simply given a voice to those already opposed to the incumbent Iranian government? Or have they acted as a catalyst, enabling a population whose access to information and discussion was previously more closely controlled to see that there are alternatives within their grasp?

These aren’t questions with simple answers, of course, and there are many other factors at play in a world where everything is changing faster than ever before. But I think it’s fair to suggest that the internet is one of the strongest disruptive forces on the gameboard, especially in countries where state control of media has been far more crude and heavy-handed than here in the privileged West.

I fully expect we’ll be seeing a lot more stories like this from developing nations in years to come, as affordable communications technology pulls aside the heavy curtains of the state… it’s good news for oppressed citizens, certainly (at least in the short run), but for global stability? Maybe not so much.


A new use for social networking technology: examining patents

Edward Willett @ 23-02-2009

patent drawings The possibilities (beyond merely sharing the latest embarrassing YouTube video or cat-based humour) inherent in today’s social networking technology are just beginning to be explored. A group of researchers in Pennsylvania suggests one possible use is to help deal with the enormous backlog in patent applications (a backlog that directly impacts how quickly new technology makes its way into society) by helping to identify what’s known as “prior art” (which, as Wikipedia–which seems a particular apt source for this item*–explains, “constitutes all information that has been made available to the public in any form before a given date that might be relevant to a patent’s claims of originality. If an invention has been described in prior art, a patent on that invention is not valid.”). (Via Science Blog.)

“The burgeoning backlog of patent applications at the US Patent and Trademark Office (USPTO), several hundred thousand in any year, has created an urgent need for Office reform,” the team explains, “Review of related application reference material, or prior art, is a necessary but time-consuming step in the patent process.” If prior art can be identified early in the assessment process then a patent claim can be discarded quickly and the patent examiner move on to the next claim.

Peo and colleagues explain how the USPTO initiated a pilot project that uses social networking software to allow groups of volunteer review experts to upload prior art references, participate in discussion forums, rate other user submissions and add research references to pending applications. The aim was to allow the actual patent examiners to focus on reviewing the most relevant prior art associated with any particular submission and so streamline the overall application process.

The pilot project, Peer to Patent, has proven successful enough (here’s its one-year report) that similar approaches are being investigated by the UK Intellectual Property Office and the European Patent Office.

*Particularly apt because there’s an unofficial patent review site called Wikipatents.

(Image: Drawing from Canadian patent awarded to my grandfather-in-law)

[tags]inventions,social networking,patents,Wikis[/tags]


Chessmen that debate every move

Edward Willett @ 16-02-2009

democratic chess When I first read about the “Democratic Chess Set” I thought it was going to be some kind of political satire aimed at the U.S. Democratic Party (“It’s just like regular chess, except you throw borrowed money at everything that moves while yelling ‘Stimulus! Stimulus!’. The first player to use up $1 trillion wins!”). But instead (Via Gizmodo):

Democratic Chess is a work in progress, the idea  derives from  Lewis Carroll´s “Through the looking glass”. The  book is based on a game of chess played on a giant chessboard with fields for squares. Most main characters met in the story are represented by a chess piece, with Alice herself being a pawn.

Democratic Chess is Chess game where each figure is made of an IP-WLan-network camera each capable of looking around, listening and talking to the other figures as well as the 2 real person players. With this technology there are many different ways how to play the Game, the next move can be decided in a democratic way among the Figures or they are allowed to discuss with the players and each other the next moves, but at the End the 2 player make the moves.

It’s the brainchild of designer Marco Marcovici, who says the technology is already working and he hopes to have a prototype shortly…but there’s no detail beyond what’s quoted above.

Now, personally, being the committee-adverse type that I am, the thought of what’s essentially chess-by-committee appals me. Still, it’s an interesting concept, combining elements of social networking and telepresence with an ancient game.

What other board–or other–games could it be applied to?

(Image: ArtMarcovici.)

[tags]games,chess,telepresence,social networking[/tags]


The future of social networking

Tom James @ 08-07-2008

Where is social networking going exactly? Will Facebook still exist in a recognisable form in 100 years? (I’d say certainly not). Some people are of the opinion that “social networking” is a con designed to persuade people to part with marketable information:

Perhaps [people will] realise that web 2.0 is not there to “connect you with the people around you” and not about some pseudo-academic “social graph”. That’s the bait. The switch is the big data centre pumping adverts based on your age, where you live, who you’re friends with, what you like doing for fun, your politics and your grandmother’s shoe size.

This leads to many interesting debates about who owns the data held on social networking websites, and how much the whole shebang is worth.

My social networkThe problem with exponential growth and constant change is that you can’t tell if something is a flash in the pan or a long term trend.

It seems likely that people will continue to use communication networks to socialise, but that they will become less tied to a particular social networking website, given the systems produced by companies like Plaxo, which (if their guff is to be believed ) allows you to integrate stuff belonging to you and your friend’s from other social networks into one area.

[stories from Technology Review and The Register][image from luce legay on flickr]


Next Page »