DIY Investor Magazine
/
March 2014
21
Initial Claims Unemployment Insurance (Thousands)
University of Michigan Social Media Job Loss Index
Sources: Initial Claims Unemployment Insurance (seasonally adjusted), U.S. Department of Labor, Prediction, University of Michigan Social Media Job Loss Index
440
420
400
380
360
340
320
Jul 16, 2011
Oct 01, 2011
Dec 17, 2011
Mar 03, 2012
May 19, 2012
Aug 04, 2012
Oct 20, 2012
Jan 05, 2013
Mar 23, 2013
Jun 08, 2013
Aug 24, 2013
Nov 09, 2013
Jun 25, 2014
Apr 05, 2014
Initial Claims
Prediction
The above image shows how twitter sentiment is
currently being used to predict US unemployment
claims, a major macro economic indicator.
By processing millions of tweets and calculating the
sentiment of the general public The University of
Michigan has started to show a correlation with the
official figures being released.
Other companies, such as Heckyl, have taken on these
challenges and are refining the process still further to
calculate even more accurate forecasts of US Jobless
Claims.
SENTIMENT ANALYSIS: THE
WAY FORWARD
Many companies have started to adopt Sentiment
analysis in taking key decisions and it is now becoming
accessible to retail investors also. State of the art
algorithms are continuously being researched and
implemented to improve the efficiency of Sentiment
analysis.
These will only get better as they are refined and the
number of users and content from the sources, such
as twitter and blogs, continue to increase. We are
in middle of an era of information explosion, where
assimilating all the information is no longer feasible.
Sentiment quantification is the answer to this and the
applications of sentiment analysis are infinite.
SENTIMENT IS A VERY VERSATILE TOOL,
WHICH CAN ADD NEW DIMENSIONS TO
BOTH FUNDAMENTAL AND TECHNICAL
ANALYSIS. WHILE DOING FUNDAMENTAL
ANALYSIS, SENTIMENT EQUIPS THE
INVESTOR WITH USEFUL PRIOR
KNOWLEDGE ABOUT THE SECTOR.
