Can Twitter Mood Predict the Stock Market?
This academic paper says Yes, here's the abstract, watch CNBC video above:
"Behavioral economics tells us that emotions can profoundly affect individual behavior and decision-making. Does this also apply to societies at large, i.e. can societies experience mood states that affect their collective decision making? By extension is the public mood correlated or even predictive of economic indicators?
Here we investigate whether measurements of collective mood states derived from large-scale Twitter feeds are correlated to the value of the Dow Jones Industrial Average (DJIA) over time. We analyze the text content of daily Twitter feeds by two mood tracking tools, namely OpinionFinder that measures positive vs. negative mood and Google-Profile of Mood States (GPOMS) that measures mood in terms of 6 dimensions (Calm, Alert, Sure, Vital, Kind, and Happy). We cross-validate the resulting mood time series by comparing their ability to detect the public’s response to the presidential election and Thanksgiving day in 2008.
A Granger causality analysis and a Self-Organizing Fuzzy Neural Network are then used to investigate the hypothesis that public mood states, as measured by the OpinionFinder and GPOMS mood time series, are predictive of changes in DJIA closing values. Our results indicate that the accuracy of DJIA predictions can be significantly improved by the inclusion of specific public mood dimensions but not others. We find an accuracy of 87.6% in predicting the daily up and down changes in the closing values of the DJIA and a reduction of the Mean Average Percentage Error by more than 6%."
HT: Peter Parlapiano
11 Comments:
there big flaw in this analysis is that it's (at best) a coincident indicator on a daily basis.
mostly, it's telling you what already happened. can it predict tomorrow? can it predict inflection points during days?
there is not value to be gained from knowing everyone is happy and the tape is already up.
This is why people should stop saying how bad everything is.
Realistically speaking, things are not perfect, but they are not as bad as you keep hearing. Saying it is bad does make it worse.
The data show the Calm series (lagged by three days) is more reliable at extreme and high levels than at extreme and low levels.
There are some indicators that are reliable at extreme levels, although not always reliable, and those extreme levels are rarely reached (e.g. a few times a year).
However, the more people who learn about and use a reliable indicator, the less reliable it becomes.
The Twitter analysis may be predictive of the VIX index ("fear, uncertainty and doubt"). The paper cited states that combining the factors "Happy" and "Calm" produce a predictive direction (market) accuracy of 80%. It would be interesting to overlay "Happy" and "Calm" over a VIX chart for the same period and see if the VIX direction has been predicted.
BTW, it seems that Twitter would be more younger oriented but the people with the wealth to determine market values are older.
Fascinating. Causality is not shown, nor is it predictive but it does show how little we know about our own collective behavior.
I have observed situations in which people panic. Box is right, thinking bad things makes things worse.
The more people learn about reliable indicator .............
--------------------------
So the market is neither rational nor efficient?
Hydra, everyone in the market doesn't have perfect information.
I'd say, the market is perfectly rational, based on imperfect information, and inefficient, until the perfect information catches-up to the market.
hydra-
"So the market is neither rational nor efficient?"
no, precisely the converse. once everyone is aware of an indicator, it gets priced in and therefore stops working.
that is a sign of efficiency.
Hmmm, makes me wonder if a group of people could conspire to and then twitter folks into thinking one way or the other regarding the stock market?
It's not surprising that one's mood is going to positively or negatively effect investment choices and that collectively this can have a measurable effect on the stock market. What's impressive is that someone has figured out how to measure collective mood based on short text tweets and then correlate that with the DJIA data.
Post a Comment
<< Home