Every year, editors at the Wall Street Journal would post stock tables on a wall, and throw darts at it, to come up with a randomized list of potential winners and losers for the year ahead. Then, a year later, the editors compared their dartboard predictions against those made by Wall Street analysts. Most of the time, the informed analysts don’t do much better than the random dart tosses.
So even the most informed analysts who study all the financial charts can’t tell what’s ahead in the market. But can the wisdom of crowds — expressed through social networking sites such as Twitter — reveal upcoming patterns? We already have wisdom of crowds at work on a preponderance of projections via online prediction markets, with InTrade being a prime example.
Online markets such as InTrade involve people putting money into their forecasts. The odds of a certain event occurring go up as more money is is bet on that event. But are there also more emotive metrics that can predict if something is going to happen? That’s what a group of researchers recently concluded, employing algorithms that gauge the calmness or agitation of Twitter posts, predicting moves to the Dow Jones Industrial Average up to three days ahead of time. The researchers, Johan Bollen (Indiana Unviersity-Bloomington), Huina Mao (Indiana University-Bloomington) and Xiao-Jun Zeng (University of Manchester), claim accuracy of 86.7 percent between their Twitter-based predictions and the actual Index.
So, there is a relationship between moods and moves, they conclude. They initiated the study to find out if societies can experience “mood states that affect their collective decision making.” And, they ask, “by extension is the public mood correlated or even predictive of economic indicators?” Apparently a connection can be made. (Full paper available here.)
The researchers admit, however, that they don’t know why this connection seems to exist. “It’s reasonable to assume that people’s moods will have some effect on their investments, but more research is needed to figure out exactly how,” Bollen told Wired magazine.
The connection between mass psychology and national events has always been an interesting one. I remember reading an article in Psychology Today a long time ago that suggested that wars tend to come along after a period of rising expectations within a public mood.
To connect Twitterverse moods with market moves, the study’s authors explained that they analyzed “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 six dimensions (calm, alert, sure, vital, kind, and happy).”