Fewer verbs and nouns in financial reporting could predict stock market bubble, study shows


Fewer verbs and nouns in financial reporting could predict stock market bubble, study shows

When the language used by financial analysts and reporters becomes increasingly similar the stock market may be overheated, say scientists.
After examining 18,000 online articles published by the Financial Times, The New York Times, and the BBC, computer scientists have discovered that the verbs and nouns used by financial commentators converge in a ‘herd-like’ fashion in the lead up to a stock market bubble. Immediately afterwards, the language disperses.
The findings presented at the International Joint Conference on Artificial Intelligence, Barcelona, Spain, on Tuesday 19 July 2011, show that the trends in the use of words by financial journalists correlate closely with changes in the leading stock indices.
“Our analysis shows that trends in the use of words by financial journalists correlate closely with changes in the leading stock indices - the DJI, the NIKKEI-225, and FTSE-100,” says Professor Mark Keane, School of Computer Science and Informatics, University College Dublin, who was involved in the research.
“By plotting the distributions of words used in financial articles published online between 2006 and 2010 into a computer model, we were able to identify what we call ‘verb convergence’ and ‘noun convergence – where the language used by financial journalists shows converging agreement.”


Graph showing an 8-week geometric mean of alpha-term in weekly verb distribution mapped against DJI
“Our study shows that reporters converge on the same language - ‘stocks rose again’, ‘scaled new heights’, or ‘soared’ - as their commentaries became more uniformly positive in the lead up to the 2007 crash.”
“They also appear to refer to a smaller-than-usual set of market events – presumably because of an increased fixation on a small number of rapidly rising stocks,” explains Professor Keane.
“Google predicted car sales from analyses of search queries, and the Amazon book recommender system captures consumer preferences by correlating book titles, so why not listen to the language used by financial commentators to see if it could help predict the stock market,” says Aaron Gerow, who completed the research as part of his MSc in Computer Science at University College Dublin and is currently studying for his PhD at Trinity College Dublin.

__________________
"Patriotism means being loyal to your country all the time and to its government when it deserves it."-- Mark Twain

"Inter arma silent Musae"--when the weapons speak, the muses fall silent.

An't nanum hearm deth, doth hwaet ye willath.

It is forbidden to kill; therefore all murderers are punished
unless they kill in large numbers and to the sound of trumpets. -Voltaire

Economic Left/Right: -3.88
Authoritarian/Libertarian: -4.36

Interesting what you can do with computer crunching power. That being said, as a phenomenom, that idea of looking at the press for counter-cyclical cues is known... and used. I think there was also something about the amount of positive vs. negative stories/headlines...

__________________
Unless otherwise specified, I am posting as a regular poster. When I will act as a mod, I'll make sure you're in no doubt.

Seems a bit similar to something I read about in Danger Room, the US's new intelligence scheme (scam?) in Afghanistan, Nexus-7. The principle here is fairly sound, in that they hope to correlate all sorts of disparate data sources to produce some kind of graphic showing where the war is being "won" and "lost". This rests on one demonstrable correlation, between fruit prices and levels of violence: they are either high or low simultaneously, and prices get spikey when violence is rising or dropping. But they are having serious trouble finding enough data to crunch and its not clear that anything much will come of it. Another thing they wanted to look at is frex changes in traffic patterns which might suggest local drivers fears of hostile activity on a road, or the presence of insurgent roadblocks etc. But the principle is probably fair enough, and is a case of using sheer processing power to come at a problem obliquely.