According to researchers at the University of California, who teamed up with researchers at Yahoo! in Spain, Twitter enables us to read patterns within Twitter streams that might be able to let us predict trends in stock prices.
Where most other studies that have looked at this question by measure the correlation between Twitter and stock prices based on sediment the UoC study ignored sediment and instead looked at the volume of tweets and how they were linked to each other.
The idea was to look at Twitter more as a network of data rather than a bunch of people talking about stocks. By using this method the researchers were able to beat out other baseline strategies by between 1.4 and more than 10 percent, as well as the Dow Jones Average over a four month period.
This was done by gathering the daily closing price and number of trades for 150 randomly selected stocks for the Standard & Poors 500 during the first half of 2010. At this point they created a program to filter in those tweets that were relevant to those companies during that period of time.
Their findings were nuanced: the number of trades seemed to be correlated with the number of tweets they labeled “connected components” – the number of distinct topics (such as the CEO’s actions, a new product and someone leaving the company) being discussed about that company that day – rather than the sheer volume of tweets. And they found that stock prices were slightly correlated with “connected components” as well.
via All Twitter
It is also good to remember that one of the first people to really get the power of Twitter were the people who play for real in the stock market and that StockTwits was one of the first third party services built on top of Twitter that took off like crazy.
