Hedge Fund Beats Market by Mining Twitter Feeds

A hedge fund is using the social networking site Twitter to gauge market sentiments, a strategy that helped the new fund beat the S&P 500-stock index and post a 1.85 percent return in its first month, according to Financial News.

Derwent Capital randomly scans 10 percent of a particular sample of Twitter feeds, or "tweets," and then classifies them into a range of silos reflecting varying investor sentiments. The idea is that "alert," "vital" or "happy" sentiments can help make predictions about the direction of stock prices. Initial research has shown that the fund's algorithm predicted movements in stocks with 88 percent accuracy, according to the Financial News.

In March, Derwent's founder, Paul Hawtin, told Financial News that he was very confident about the Twitter strategy. "We watch to see how each of the different mood states changes in real time. The biggest sentiment change is reflected in the market around two to four days later," he said. Hawtin added that it's the unprecedented global nature of Twitter that defines its use as a sentiment tool.

Critics of Twitter claim the social networking site is a pastime of teenagers whose sentiments have little correlation to the ebb and flow of the capital markets. Yet, Twitter has 200 million followers worldwide, and their tweets are delivered in real-time.

Financial News said that studies from Indiana University and Great Britain's University of Manchester indicate that certain words conveying emotion on Twitter can influence moves in the Dow Jones industrial average.