The Dow of Tweet

article image
Juan Carlos Solon /

What’s the old adage? Buy low, sell when Twitter’s sad? Is that it? If not, maybe it’s time for a tweak, because according to a story on Wired‘s website (Oct. 19, 2010), “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.”

Attempting to divine the mood of the public through Tweets, social scientist Johan Bollen and graduate student Huina Mao used a questionnaire that attaches adjectives to feelings. After searching millions of Tweets for those adjectives, Bollen and Mao figured they could gauge the general mood of the American public. Mao compared that mood to the Dow and found that the emotional tenor of Twitter traffic seemed to predict what would happen on the stock market a few days later.

To test this unexpected coincidence, the two used the mood information in conjunction with an algorithm that predicts the fluctuations of the stock market with an accuracy of 73.3 percent. When Twitter’s mood was factored in, the algorithm’s accuracy shot up to 86.7 percent.

Although more research is needed to understand why this happens, maybe it’s time to tell your stockbroker that she should be spending a little more time shuffling her TweetDeck.

This article first appeared in the January-February 2011 issue of Utne Reader.

In-depth coverage of eye-opening issues that affect your life.