Friday, October 22, 2010

Twitter Mood Data Predicts Market Activity

The millions of messages sent daily via San Francisco-based Twitter can help predict moves in the Dow Jones Industrial Average by analyzing sentiment, said researchers at Indiana University and the University of Manchester.

By scouring tweets for key words and analyzing them using an algorithm they developed to divine the mood of Twitter users, Johan Bollen, Huina Mao and Xiao-Jun Zeng said they were able to predict the daily up and down movements of the Dow during a period in 2008 with 87 percent accuracy.

Bollen's team outlined their findings in a paper published Oct. 14 on, an on-line journal. The team trawled through 9.9 million tweets using two tools, one called OpinionFinder which sorts messages into either positive or negative moods, and another from Google, which classifies text into six mood dimensions: calm, alert, sure, vital, kind, and happy. While the OpinionFinder data was not very good at predicting stock market movements, one of the Google dimensions, calm, was excellent.

"Changes of the public mood along these mood dimensions match shifts in the DJIA values that occur three to four days later," the team said. "The aggregate of millions of tweets submitted to Twitter at any given time may provide an accurate representation of public mood and sentiment."

I think the researchers have something here, as what they are collecting is data on real individuals and their views at a specific time.

Hedge funds will jump on this and have models up by the end of next week for the obvious sentiment indicators. But there likely will be profit potential for others who can think of unusual sentiment indicators.

The researchers should have kept this one to themselves. It sounds like a big moneymaker to me.

No comments:

Post a Comment