Twitter analysis could predict stock market movements says Cornell

New research indicates Twitter has the potential to predict economic indicators and even predict the movement of the stock market.

A study from Cornell University, posed the question ‘Is the public mood correlated or even predictive of economic indicators?’ The researchers investigated whether measurements of collective mood states derived from large-scale Twitter feeds are correlated to the value of the Dow Jones Industrial Average (DJIA) over time.

According to an article in PCWorld, the research stemmed from the documented belief that the ebb and flow of the stock market is driven by decision making instead of reaction to news. The study looked at 10 months’ worth of tweets from almost 3 million users, focusing specifically on tweets about feelings.

The researchers analysed the text content of daily Twitter feeds by two mood tracking tools, – OpinionFinder that measures positive vs. negative mood and Google-Profile of Mood States (GPOMS) that measures mood in terms of 6 dimensions (Calm, Alert, Sure, Vital, Kind, and Happy).

Significantly, the research indicated a high percentage of prediction accuracy. The researchers said “We find an accuracy of 87.6% in predicting the daily up and down changes in the closing values of the DJIA and a reduction of the Mean Average Percentage Error by more than 6%.”

Cornell’s findings support the conclusions of our own research, released in June that suggested companies not using social media for investor relations purposes were missing out on influencing share price.