Sorry!! The article you are trying to read is not available now.
HOT TAGS:  

Forget Long-Winded Wall Street Research Notes, Twitter Predicts Stock Market in 140 Characters Or Less

Print comment Post Comments
ANNALS OF DUBIOUS PROGRESS
DailyFeed
The MIT Technology Review reports that Johan Bollen at Indiana University claims to have figured out how to predict stock market moves up to six days in advance by analyzing messages sent via Twitter.

Bollen utilized an algorithm, called the Google-Profile of Mood States (GPOMS), that records the level of six states: happiness, kindness, alertness, sureness, vitality and calmness.



Going on the belief that the rise and fall of stock market prices is influenced by the public mood, Bollen took 9.7 million tweets posted by 2.7 million tweeters between March and December 2008 and looked for correlations between the GPOMS indices and whether Dow Jones Industrial Average rose or fell each day.

Their conclusion? There really is a correlation between the Dow Jones Industrial Average and one of the GPOMS indices--calmness.

"We find an accuracy of 87.6% in predicting the daily up and down changes in the closing values of the Dow Jones Industrial Average," says Bollen.

There are, of course, scientific holes all over Bollen's experiment.

But crazier things have attracted a heckuva lot of interest.

Collectible gold coins, anyone?
POSITION:  No positions in stocks mentioned.

TICKERS