DIY Investor Magazine
/
March 2014
18
THE POWER OF THE CROWD
We live in an age of too much information and yet, we
do not have access to the right information, at the right
time. An accurate quantification of the sentiment of
relevant text that is published online (referred to here
as the sentiment score), can help solve this daunting
problem.
There are two main aspects that we will be examining
in this article: what types of problems can sentiment
analysis help solve, and how complicated is sentiment
analysis?
CONSUMER SENTIMENT:
REVEALING THE FACTS
Sentiment analysis of open online sources now
provides the most accurate view of customer feedback
and satisfaction. More importantly, sentiment analysis
over time can show investors which direction a
particular company is heading. For example, after the
release of Apple’s iPhone 4s, the media perception of
the device was by and large negative.
However an analysis of twitter sentiment for the
phone revealed a positive consumer trend, and
after 3 months it was declared to be a blockbuster
product, with the associated affect on the share price.
Consumer sentiment is the only way to differentiate
facts from perception.
However sentiment analysis is not only about looking
at sentiment direction (positive / negative). In another
incident, there was general negative sentiment on
twitter following the recall of a car model from
Toyota in 2009, with people across different regions
complaining of issues with the car.
But when a respected person spoke negatively about
it, there was a sudden drop in the share price. This
shows that the intensity of impact will also be
affected by the reliability and standing of the source
and weighting associated to it.
DYNAMICS OF SENTIMENT
QUANTIFICATION
When looking for a sentiment score, particularly in
finance, where every event is connected to multiple
incidences, the whole ecosystem acts as a contributor.
For example when a drug is recalled by a Pharma
company, the algorithm to quantify the sentiment
of that news will look up multiple aspects, such as if
the drug was patented or generic, as a patented drug
will have a much higher impact on the share price, as
compared with the generic drug.
Also is there any recent news about the company, such
as has any other drug trial recently failed or has the FDA
commented negatively on other trials, as well as many
other aspects. Sentiment scoring algorithms go much
further than just looking at the volume of keywords
present, they consider the entire ecosystem before
quantifying and scoring it.
USING SENTIMENTS FOR
FUNDAMENTAL AND
TECHNICAL ANALYSIS
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. Recently a sudden awareness of environmental
hazards of palm oil, created deep negative sentiment
on social media and blogs for Proctor & Gamble. The
company has now changed its manufacturing procedure
for those lines of products, however potential investors
could have been forewarned by analysing the trending
sentiment of the company in question.
For technical analysis Sentiment time series analysis,
can provide a lot of information about the company’s
timeline and is a very strong indicator along with
volume and moving average. Companies are now
performing analysis to predict trend reversals in share
prices, using sentiment direction as indicators along
with frequency of tagged words, weighing of sources,
volume and price data; which gave results with an
accuracy in excess of 70%.
Gustav Pegers,
Head of Sales at Heckyl, provides a quick introduction as to how sentiment
analysis is helping people sift through the overload of online information now facing investors.
