Slashdot Mirror
Real-World Outcomes Predicted Using Social Media
Hugh Pickens writes "Kevin Kelly writes that researchers at the Social Computing Lab at HP Labs in Palo Alto have found that social media content can predict real world outcomes. In their study, the researchers built a model that used chatter from Twitter to predict accurately the box-office revenues of upcoming movies weeks before the movies were released. When the sentiment of the tweet was factored in (how favorable it was toward the new movie), the prediction was even more exact. To quantify the sentiments in 3 million tweets, the team used anonymous workers from Amazon's Mechanical Turk to rate a sample of tweets, and then trained an algorithmic classifier to derive a rating for the rest. But predicting box office receipts may be only the beginning. 'This method can be extended to a large panoply of topics [PDF], ranging from the future rating of products to agenda setting and election outcomes,' the researchers write. 'At a deeper level, this work shows how social media expresses a collective wisdom which, when properly tapped, can yield an extremely powerful and accurate indicator of future outcomes.'"
Predicting what a bunch of assholes who use twitter will do.
These social network predictions were already predicted by the late Mr. Asimov. ;)
The larger your sample size the more accurate your results tends to be. Fascinating.
Tweet incorrectly about the next election to screw with the people tracking this.
I watch Social Media mentions of things I care about very closely. I've explained to others how I've come to realize there is a definite "canary effect" with the mass sentiment seen via real-time opinion/view venues such as Twitter.
In fact, for items related to "down time" of sites people are routinely faster at registering their dismay at a service being unavailable than expensive site monitoring tools. This isn't exactly predicting future outcomes, but it is an "early warning" indicator that businesses should tap into.
Personally, I use simple scripts that hit the Twitter Search API and send alerts to me and others via IM, email, etc. Not as pretty as $2000/mo monitoring systems, but quite effective.
-- @rjamestaylor on Ello
At a deeper level, this work shows how social media expresses a collective wisdom which, when properly tapped, can yield an extremely powerful and accurate indicator of future outcomes.
In other words - Never underestimate the power of stupid people in large groups.
A candidate makes a speech, and then the workers scrape SN data to see the response, so the candidate can further tailor the message for the next speech. However, do we really want to always be driven by public opinion?
The fact that the tweets predict the sales in advance of the movies release or people actually seeing the movie raises an interesting question. Is it the content of the movie or the "buzz" that really matters?
Statesman
Is this an early experiment in the development of psychohistory?
Hari Seldon would be proud.
...I've always like that word. I so rarely have a chance to use it in a sentence.
Sorry about the mess.
The true demise of twitter will be / is when the PR firms that try to take advantage of this flood it with spam, or worse yet, pay people to hype their junk.
Onwards to the next social networking platform!!! I want something with pub/private encryption, non-repudiation, recall, key escrow, supports live pictures, movies, sound, and sound effects, multi-threaded conversations, geolocation, rankings, tagging, filtering, and stuff (yes, I know I contradicted myself a few times, laugh)
"'At a deeper level, this work shows how social media expresses a collective wisdom which, when properly manipulated, can yield extremely powerful and profitable future income..'"
- Fixed That For You.
So let me get this straight. A research institution came to the conclusion that popular things tended to earn a lot of money, while unpopular things tended to tank?
Holy Crap stop the presses! We just invented the Oracle of Delphi! It's all so clear now. The Greeks weren't talking to the gods, but they were talking to a complicated trend analysis computer that tapped into their far reaching social networks!
=P
Nah, in all seriousness though, it's a pretty interesting read.
Motorcycles, Robots, Space Gossip and More!
This might work right now but start using it for anything useful and it will get spammed relentlessly.
Google's organic search results have the same problem. So many SEO people and companies are manipulating the results that most searches are now pointless.
Who are the people acting as the "Mechanical Turks" in this case? Are they Americans who are actually familiar with American cinema and culture? Or are they Indians, Africans and other third-worlders who have limited Internet access, but don't necessarily have access to American culture and movies?
I've always understood that Americans can't make much money at all acting as these "Mechanical Turks", but third-worlders can. What's the reality here? How much can an American make acting as a "Mechanical Turk"?
I don't think that the terms social media and collective wisdom can be appropriately used together in a sentence. Unless you are describing the lack of wisdom thereof.
Ok guys. So when the next Joss Whedon series comes out, everyone tweet about how great it is.
I have have mod points but no way to mark this -1 Fail.
Wikipedia says:
The Delphi method is a systematic, interactive forecasting method which relies on a panel of experts.
Of course, in this case the "experts" are the movie-going public, who know more about their tastes in movies that anyone is Hollywood. The Delphi method depends on large panels, and n this case th researchers are using large panels indeed. Finally, the iteration is provided by the later tweeters reading earlier tweets before they post.
Nothing for 6-digit uids?
seems more like viral marketing effect felt on twitter...
I can see it already. Someone in Wall St is look at this thinking they can automate their buying and selling of stocks and beat the market, then they'll say they aren't making enough so they'll create a derivatives market in social media futures, then they'll fiddle things slightly to improve it, then when the bubble bursts (again) we'll look back at this and wonder why it happens again and again.
Putting the fact that increasing sample size does not necessarily increase the power of a predictor, you apparently didn't get the point of their method.
So method A was to simply "grep RamboIX" in these 3 million tweets. That alone already correlated to the box office outcome. However, that also catches messages like "RamboIX suxx, no way I'm going to see or even download this".
So method B was to use machine learning algorithms, combined with some initial work by human drones, to assign a degree of "positiveness" to each message about RamboIX.
While this has nothing to do with increasing sample size, it took the accuracy of the prediction to a whole new level.
I for one think this is a pretty great idea.
Collective wisdom? In today's popular culture? Surely there must be a better term than that.
Yes, 'the crowd' generally has a pretty good idea of what 'the crowd' is going to do.
If you ask me if I'm going to go see a movie or not than my answer is probably going to pretty accurately reflect what I'm actually going to do.
I'm not exactly sure why this is surprising? Marketers have been doing this for years. They announce products that haven't even hit the drawing board yet. If they get a good response in the form of inquires and other types of interest, they build the device. If they don't then it will just go away.
Persistent Volume manager for Kubernetes - https://github.com/dwimsey/openshift-pvmanager
I'm glad they tested this on something important like movie revenues.
Would be a shame to waste power like this on something like election outcomes.
Forget the mechanical turk. Just tell me the marketing budget of a movie and how many screens it's going to open on and I'll give you an estimate of the take. It's a pretty strong correlation on large-release movies.
Hollywood has worked so hard to remove the actual quality of the movie from the equation. Get the movie onto a lot of screens early and spend a lot on advertising. Get people in to see it on the first 3 days (Fri, Sat Sun, or Wed-Sun in some cases) before any info about the movie that you don't control (i.e. other than promos) gets out.
Many movies make around half their total theatrical take in the first weekend of release.
http://lkml.org/lkml/2005/8/20/95
The quote in the article is such crap:
At a deeper level, this work shows how social media expresses a collective wisdom which, when properly tapped, can yield an extremely powerful and accurate indicator of future outcomes.
No it doesn't show that at all. It shows that what is popular in twitter is popular in the real world. In other words, it shows that twitter is close enough to a representative sample of the general population for many practical purposes. That is all. It doesn't have anything to do with collective wisdom, nor does it help you predict any outcome unless it is primarily dependent on popular opinion.
How resistant would this be to Ford Edsel-like hype? Would we get another one of these?
These days I would consider that an oxymoron..
For justice, we must go to Don Corleone
Here's a prediction based upon social networks:
People will become increasingly self-absorbed and focused on triviality and consumption.
During this Holy Week, I think we should all remember that when you post on Facebook or Twitter, it makes Jesus cry.
And it makes Buddha do the "finger down your throat" sign for puking.
You are welcome on my lawn.
But predicting box office receipts may be only the beginning. 'This method can be extended to a large panoply of topics, ranging from the future rating of products to agenda setting and election outcomes,' the researchers write. 'At a deeper level, this work shows how social media expresses a collective wisdom which, when properly tapped, can yield an extremely powerful and accurate indicator of future outcomes.'
Hey, how about using this for something that's actually useful, like predicting and preventing attempts at suicide?
Oh, say does that Star-Spangled Banner entwine / The myrtle of Venus with Bacchus's vine?
Wow. It's like psychohistory - uh, wait - isn't this really just doing a poll? Hasn't this already been done for decades? Just poll a small number of people in the general population, and you can "predict" all kinds of things - like elections before they happen? Sigh. The only difference between this and regular polls is that this is less scientific (since they make no effort to find a random selection of people from the population). It's probably a little better than online polls (probably less manipulation) and a little worse than scientifically-designed polls.
Tweet millions of times about your product to fool your investors and other interested parties.
Currently hooked on AMP
http://www.bloomberg.com/apps/news?pid=20601204&sid=aBtiaTy.Q1vw
"The Motion Picture Association of America asked regulators to reject proposals from two planned exchanges that would allow investors to trade in movie futures.
Approving movie futures contracts would be the "economic equivalent of legalized gambling," MPAA interim Chief Executive Officer Bob Pisano said in a letter March 23 to the Commodity Futures Trading Commission.
The Cantor Futures Exchange, a unit of Cantor Fitzgerald LP, and Trend Exchange, backed by Veriana Networks LLC, are seeking approval to create markets that would permit investors to trade on futures based on box-office receipts before a film is released. Cantor would be open to individual and institutional investors while Trend Exchange would be limited to institutions.
"
""The reputation and integrity of our industry could be tarnished by allowing trading in the movie futures contracts," Pisano said in the letter."
Can't have Hollywood movies integrity compromised can we?
The Singularity is closer than you think
Quant
if you tell everyone that it works then they all start anticipating the outcome and looking for ways to take advantage from it... and that changes the outcome.
Should've kept it secret and made your fortune. Now everyone and their dog knows about it, just watch how quickly those graphs begin to degade.
It doesn't surprise me that a few HP geeks are doing arithmetic analysis of what's supposed to be art. No doubt this model will be used to bang out a bunch of crap optimized for it, which will then disprove the model. It would not surprise me if a niche industry in punitry alts didn't spring up so that people could blog every possible permutation of like/dislike early and so market the winning alts as "market drivers" that could be marketed to studios. Why not? We're already doing that here on slashdot and other tech sites.
These guys should get laid. Then maybe they'd put down the slide rule and enjoy the movie.
Help stamp out iliturcy.
The only difference between this and regular polls is that this is less scientific (since they make no effort to find a random selection of people from the population). It's probably a little better than online polls (probably less manipulation) and a little worse than scientifically-designed polls.
Judge for yourself, here's what they say:
Surprisingly, we discovered that the chatter of a community can indeed be used to make quantitative predictions that outperform those of artificial markets. These information markets generally involve the trading of state-contingent securities, and if large enough and properly designed, they are usually more accurate than other techniques for extracting diffuse information, such as surveys and opinions polls.
So twitter-reading beats markets which beats polls.
Also, what do you mean by "scientifically"? If you mean "like scientists", could you please explain to me what the important properties of what scientists do are?
POst-quark APril 1 charm Agreeably hard to distinguish true content from false on this year's Topeka date. Twitterers driving Hollywoood seems well pitched close enough to the believability threshold to cause real doubt. Every day I read Slashdot expecting to be on the boundary between the beliebavle and the possible but not yet practical. As someone who prefers the bright haze of a documentary to the potential fuzz of fiction I wonder is the appeal of Slashdot: the be the source in reality for the sciFi desire in our day-job bound reality-needing souls? I certainly open it looking for that "could it be?" buzz. PS. Talking virtual reality, has anyone detected the potential typo of hadron for hard-on?
--- The Battle of the Titans has been established in a town of the (middle West?) famed for drag racing, bike jumps across gulches and similar macho standoffs. Turned-on-technologists from all States convene for the Battle of the Schwarz. (Der Schwarzbattelgotterdammerunggesellschaft) Two champions, representing their respective armies, face off on the Plain. Passions rise. Injuries are attempted. Few occur. (Spirit willing, but..) Finally tempers abate and the parties go home, deflated but having had their Day On the Plains, confronting the greatest of their generation.
http://www.halfpasthuman.com/