news sentiment system needs to do more than just determine the news sentiment for the
user to be able to understand and correctly assess news sentiment impact.
For instance, a news sentiment system needs to communicate to a user how
assessment of the sentiment has worked in the past. As such, the system should be able
to create historical and real-time reports that show stock price movement along with the
news sentiment for individual stock tickers.
In today’s online environment, where news about publicly traded companies may be
found on a multitude of news sites and social networks, the ability to determine the true
impact of a particular news article is diminished. One example is the effect that a social
network such as Twitter can have not only in accelerating news distribution but also in
actually creating more news.
A news sentiment system should be able to provide a level of assurance that there is a
credible, direct impact of a certain news item on stock price movement. In other words, a
news sentiment system should be able to allow users to correlate stock price movement
from its price immediately before the news item became public to the price reaction in
the timeframe immediately following the news release.
A news sentiment system can provide a way to better estimate and manage trading
and investment risk. By receiving a heads-up on the potential impact of the news item,
users can focus their attention on other stock price variables and make decisions faster
and more accurately than they would without the help of a news sentiment system.
One thing that a news sentiment system cannot provide is ‘‘certainty’’ in managing
trading and investment risk. News sentiment systems are not and cannot be perfect
systems. Therefore, there needs to be an understanding that there is a certain level of
accuracy and dependability in news sentiment assessment. This level needs to be com-
municated directly to the user via real-time and historical reporting, correlation analysis,
or any other method possible.
Ultimately, to be successful a news sentiment system should help users to improve
their current level of accuracy when determining the impact of a particular news item on
a particular stock price.
The level of that particular improvement in accuracy will most likely determine the
value of the news sentiment system when making decisions about trading, investing, or
hedging.
Considering the level of improvement in accuracy that a news sentiment system brings
to traders and investors in the current environment, the use of such a system has become
an absolute must.
4.17 Backtesting news sentiment systems
The impact of a news item is usually very short-lived and most likely represents the
perspective of the author(s) of the news item. Moreover, the impact of a news item can
also be significant and may create major changes in the life of the stock of a publicly
traded company.
Since not all news is created equal, there is questionable value regarding the use of a
backtesting system that could evaluate the impact of the news sentiment of a news item
months or even years after the news was published.
Measuring the value of media sentiment: A pragmatic view 119