Associate professor talks Twitter on CNBC

IU School of Informatics and Computing associate professor Johan Bollen made an appearance on CNBC on Tuesday for the “Twitter Predictor,” mood-tracking tools that analyze content of a large-scale collection of Twitter feeds.

“Measurements of the collective public mood derived from millions of tweets can predict the rise and fall of the Dow Jones Industrial Average up to a week in advance with an accuracy approaching 90 percent,” according to an IU press release.

Bollen and Ph.D. candidate Huina Mao analyzed more than 9.8 million tweets from 2.7 million users during 10 months in 2008.

OpinionFinder analyzed tweets “to provide a positive or negative daily time series of public mood,” while Google-Profile of Mood States “measured the mood of tweets in six dimensions: calm, alert, sure, vital, kind and happy,” according to the press release.

Bolen and Mao then correlated Dow Jones with the public mood to hypothesize that including public mood measurements could improve predicting stock market values.

“We were not interested in proposing an optimal Dow Jones prediction model, but rather to assess the effects of including public mood information on the accuracy of the baseline prediction model,” Bollen said in the release. “What we found was an accuracy of 87.6 percent in predicting the daily up and down changes in the closing values of the Dow Jones Industrial Average.”

Read Bollen’s National Science Foundation-funded research paper and watch Bollen’s CNBC interview.

— Bailey Loosemore