‘Twitter can help predict stock market movements’

‘Twitter can help predict stock market movements’

Washington: Microblogging website Twitter can help predict the swings and throws of a stock market much like or rather better than any financial analyst, scientists say.

Researchers at the Indiana University who analysed nearly 10 million tweets, or 140 character messages, found that they could predict the rise and fall of the Dow Jones Industrial Average — in some cases nearly a week in advance.

The findings, the scientists said, could help investors game the market to make a quick buck, Discovery News reported.

Jonah Bollen, an IU scientist who led the study along with Huina Mao, said: “These online environments are starting to drive real-life social phenomona."

A growing body of research is mining information from social media sites like Twitter, Facebook and blogs. Recently scientists have used this information to measure the public’s general state of happiness and to predict box office sales of new movie releases by the amount of online chatter they generate.

In this particular study, published on the ‘arXiv.org´, the IU scientists analysed nearly 10 million tweets over 10 months in 2008 from users throughout the Twitter community.

The researchers intended to find out how anxious, happy, vital, calm, sure and alert people were feeling during a politically and economically volatile year.

They were looking to see what kinds of correlations they would find by comparing the performance of the Dow Jones Industrial Average -- the oldest and single most watched index in the world -- with the mood of the Twitter-verse.

The team was able to detect a strong correlation, but only when the Twitter data was shifted back three or four days.

The IU researchers found that only calmness could predict market swings, as determined by two mood-tracking tools such as OpinionFinger and Google-Profile of Mood States.

These tools look for specific words and phrases that indicate how the Twitter user is feeling. For example, if a person tweeted “I am happy," that would influence the happiness score.

According to Bollen, the link was not just correlation, it was also causation. The calmness or anxiety of the Twitter community actually predicts the fluxes in the market, and with nearly 90 per cent accuracy, he said.

However, Brian Uzzi, a Northwestern University professor, said the IU research is limited to predicting events that have already happened. But hoped that scientists would soon be able to predict events in the future.

“The kind of predictions made by the Bollen group will be ever more finely tuned and faster," said Uzzi.

“The electronic data that has recently become available to scientists gives us unprecedented new clues into the spread of disease, how people should evacuate a city or how the stock market behaves."