Twitter Mood Predicts the Stock Market
Indiana University Researchers Bollen and Mao to discuss
their findings at the New Horizons Summit
Bollen and Mao both come from engineering backgrounds; they were eager
to obtain quantitative information on public mood, plain and simple. They
set out to use their unique data mining tools to test a new technology
and analyze social mood: at first they gave no thought to stock market
forecasting.
They both admit that they were shocked in the course of their research
to discover that their mood data seems to predict changes in the market
with 87.6 percent accuracy. They realized this challenged the traditional
view that the economy affects social mood trends.
Matt
Lampert, the Socionomics Institute's
research fellow at Cambridge, was not surprised. The week the study published,
Matt recognized the importance of Bollen and Mao's work. Socionomics posits
that social mood motivates social events (including the markets); Bollen
and Mao's work supports that premise.
Bollen and Mao's academic openness to the unexpected results of their
research has led them to consider socionomic theory as a viable explanation
for the correlations between Twitter mood and the stock market. They will
discuss their work at the 2011 Socionomics Summit.
Listen to their interviews here, wherein Bollen and Mao both discuss their
surprise at their experiment's results and the need for more research
to determine causality.
News outlets are welcome to use the audio clips above in their
reporting.
Or read interview highlights from these two highly visible academics
below:
Jill M. Noble: What did you originally expect
to find from your data collection? Did you initially set out to challenge
the Efficient Market Hypothesis and random walk theory?
Huina Mao: When we started research, we just tried
to… chart the public mood. As you know we are both from informatics.
Johan is from psychology. So we didn’t think to try and challenge
Efficient Market Hypothesis.
Then we find socionomics, we find a bunch of research supporting these
findings -- [it] makes us feel very excited to conduct more research
in this direction.
JMN: Bob Prechter, long ago, noticed that perhaps
the Dow Jones Industrial Average and different stock market indicators
can possibly indicate our optimism and pessimism primarily because
it's such a great record -- such a well-kept data set.
Johan Bollen: 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 it's 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.
JMN: I think that's where we find the information
so interesting -- because the socionomic hypothesis puts forward the
idea that it's actually aggregate social mood, this sort of patterned
collective psychology, that drives a lot of what happens in our… not
only in the markets, but in…
JB: And we've come to believe that as well -- I couldn't
agree more! 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.
Bollen, Mao, and Prechter will all be on hand at the 2011
Socionomics Summit: New Horizons in the Study of Social Mood on April
16, 2011 in Atlanta.
Members of the media are welcome to attend the Socionomics Summit.
Please contact Alexandra Lienhard, alexandral@socionomics.net
for credential information. News outlets are welcome to use the audio clips above in their
reporting.
Socionomics posits that social mood motivates social events (including
the markets); Bollen and Mao's work supports that premise.
Related
article from the Socionomics
Institute.
Find us on Facebook
or Twitter.
|