To be honest, I’m skeptical about the work in a couple of ways.
First, as some others already pointed out, correlation does not necessarily
Second, I’m not sure if it is more accurate (in predicting) than existing quantitative measurement of market calmness (or the lack of it) such VIX , or put/call ratio for an individual stock. While I don’t have any statistics, I personally find put/call ratio of GOOG is usually more informative (and direct) than reading tweets about $GOOG. Of course, their work is about the market as a whole, which I have no clue. Why their result is for 2-6 days later,
but not the next day?
Maybe the real catch of the study is, if it really works in the past and present, then people will follow the information and then the market will become fully efficient (in theory) as a result, hence the discovery will stop work after its publication. In the other words, it’s a theory that can not be falsified, and by Popper’s standard, not “scientific”. I may be to too picky…we have to wait and see if it can continue the magic.
Google trend claims that it can predict the present, not the future. I would like to say that’s a safer claim.
I do believe tweets will be even more useful in financial analysis, in
many other ways.
Twitter Can Be Used to Predict Stock Market, Say Researchers
By Sarah Perez / October 18, 2010 6:47 AM
Researchers from Indiana University have devised a method for
predicting changes in the Dow Jones Industrial Average through the analysis of Twitter updates. Using two mood-recording algorithms, the Google-Profile of Mood States (GPOMS) and OpinionFinder, the researchers analyzed 9.7 million tweets posted between March and December 2008. They found that correlations between the calmness index, one of the six “moods” measured by GPOMS, could be used to predict whether or not the Dow Jones Industrial Average went up or down between two and six days later.
Twitter Mood Predicts The Stock Market
October 18, 2010
An analysis by Johan Bollen at Indiana University and associates of almost 10 million tweets from 2008 shows how they can be used to predict stock market movements up to 6 days in advance.