acm-header
Sign In

Communications of the ACM

ACM TechNews

Wall Street Traders Mine Tweets to Gain a Trading Edge


Twitter logo

Twitter

Wall Street traders are using social networking sites, such as Twitter, and computer algorithms to decipher the mood of the public to predict market fluctuations.

The use of linguistic analysis of online posts could prompt a computer program designed to interpret the data to place a trade with no human intervention. Researchers know that emotions play a significant role in markets and analyzing millions of tweets is similar to a "large-scale emotional thermometer for society as a whole," says Indiana University professor Johan Bollen, who recently completed a study that links Twitter mood measurements to stock market performance.

Bollen used two mood-tracking tools to analyze the text of 9.6 million Twitter feeds over a nine-month period. One tool measured whether tweets were positive or negative, while the other tool categorized tweets into one of six moods. The measuring tools resulted in 87 percent accuracy in predicting Dow stock prices three to four days later, according to Bollen.

Meanwhile, Pace University's Arthur O'Connor recently conducted a study showing a positive correlation between stock price performance and the social media popularity of brands such as Starbucks, Coca-Cola, and Nike.

Market traders also are using computer algorithms to speed-read and analyze news to search for investing clues.

From USA Today
View Full Article

Abstracts Copyright © 2011 Information Inc. External Link, Bethesda, Maryland, USA 


 

No entries found

Sign In for Full Access
» Forgot Password? » Create an ACM Web Account