Twitter Mood Predicts Stock Market Changes, Study Says
In the latest effort to determine how exactly Twitter will help the world, a new study argues that the micro-blogging platform can predict movements in the stock market.
The report (pdf), authored by Johan Bollen, Huina Mao and Xiao-Jun Zeng, says that the degree of "calmness" of the Twitterverse can predict -- with 87.6 percent accuracy -- how the Dow Jones Industrial Average will move, two to six days before the movements occur (hat tip to the Awl).
To reach this conclusion, the researchers examined two already-existing Twitter "mood tracking tools": OpinionFinder, which measures positive versus negative mood, and Google-Profile of Mood States, which measures "six dimensions" of mood: alert, sure, vital, kind, happy and calm.
After double-checking the accuracy of these tools, they looked at 9.7 million tweets between March and December 2008 and determined that Twitter calmness predicts the behavior of the DJIA. They find it "surprising," they say in the report, that OpinionFinder's positive/negative indicators didn't have more influence, and that it was "calmness" that appeared to anticipate moves in the market.
The study's authors are quick to note that they have no idea why this should be the case. The researchers say their findings "offer no information on the causative mechanisms that may connect public mood states with DJIA values in this manner." While "calmness" might predict market movements, it doesn't necessarily cause them.
Also perplexing is the fact that the tweets came from around the world, and the researchers don't know how many of them were conceived in the U.S., where the DJIA is based. And of course, other influences, such as news, can trump the "calmness" factor. As the researchers put it, "The deviation between Calm values and the DJIA ... illustrates that unexpected news is not anticipated by the public mood yet remains a significant factor in modeling the stock market."
Still, as Technology Review notes, these potential flaws don't detract from the fact that the findings could be "hugely influential." If nothing else, the results suggest the influences on the DJIA extend far beyond the financial community.
"One could speculate that the general public is presently as strongly invested in the DJIA as financial experts, and that therefore their mood states will directly affect their investment decisions and thus stock market values, but this too remains an area of future research," the report says.