In the world of algorithm-based investing, you can hardly throw a stick these days without hitting someone who's incorporating social media data in their trading method.
Traders seem convinced that social chatter from a specific group or about a specific event (like a new Apple product or changing Netflix service) can be a predictor of where stocks are headed. Yet it was more than a year ago when Indiana University's Johan Bollen found that his team's Twitter sentiment analysis predicts changes in the market with 87.6 percent accuracy.
What makes Bollen's work particularly notable is that it challenges the assumption of fundamental analysis that the news drives the markets: in fact, his work suggests that collective social mood leads the DJIA closing values by a few days' time.
Robert Prechter's socionomic hypothesis stipulates that aggregate social mood is patterned, and in turn drives social activities (including the markets). It was more than three decades ago when Prechter observed that trends in the Dow Industrials and other financial markets directly reflect the optimism and pessimism of social mood.
In an interview last spring, Johan Bollen agreed:
Well, I mean, the scale of it: the number of investors and the speed at which they make decisions is tremendous. So you really have a good indicator of the public sentiment towards investing right there in the market.
The most surprising thing is that [market movement] is apparently tied into pretty non-market-related shifts in the public mood -- right? Because we've actually measured public mood states for all tweets. We haven't actually limited that to those submitted by traders or anything like that.
… The research compelled us because all the people thought it would be the news…. But I can definitely say that (Twitter mood) seems to predict the markets, and so that highly suggests some kind of causal mechanism that we don’t understand yet.
Listen to the entire interview here.
Bollen’s willingness to follow the data wherever it goes produced a result which challenges the traditional view that the economy drives social mood -- and led him to consider socionomic theory as a viable explanation for the correlation between mood as expressed on Twitter and the stock market's performance.
He and his colleague Huina Mao (interview coming in early March) will be back at the 2012 Socionomics Summit for an encore presentation.
Seats for the April 14 Socionomics Summit: New Initiatives in Research and Application in Atlanta are selling fast. Last year's inaugural event sold out.
Don't miss your chance to hear from Dr. Bollen and an impressive list of additional presenters, including Bob Prechter -- Reserve your seat now>>
The opinions expressed by conference commentators may not precisely reflect those of the Socionomics Institute. In the scientific spirit, we welcome input from contributors of all types, encourage discussion on all aspects of socionomic theory and remain perpetually open to revision.