Imagine you are handed every letter to the editor to the New York Times from 1984 through 2011, and you are asked to find every reference to the word “immigration,” take a count, and determine an underlying sentiment or pattern of thought regarding the term.
And you have 12 minutes to do it.
Yeah, right.
But just like it has revolutionized every industry, technology has provided the automated solutions and tools that can do just that—and in more like 12 seconds—with text analytics.
Basically this tool takes large bodies of text to find not just counts of terms, but through creative key term combinations and simultaneous searches, the sentiment behind the terms can be measured and evaluated as well.
This works great for all the social network activity out there right now — and which is only going to grow over time — because all the thoughts, feelings, observations, etc. that are posted on the Internet are all in the format of searchable text. New data is generated every day, in enormous amounts, and it holds rich, measurable data that can help companies keep a pulse on their reputation and the positive or negative sentiment that is out there regarding their products and services.
Text analytics can also be used internally to measure employee satisfaction, management effectiveness, reactions to change, alongside surveys and responses, to discover anything that needs discovered. The possibilities are truly endless.
We’ve done a lot of text analysis for our clients (and sometimes for a little fun), and it’s always interesting to see, not only how attitudes change around a certain topic or theme, but even how language changes in general. We know some grammar geeks and linguists who love doing text analysis to see what has happened to the language in the last 10, 20, or even 100 years.
A New Development in Text Analytics
An interesting new development in this already relatively new solution is the anonymous versus non-anonymous reaction, and what people say and how they say them if they believe their comments are anonymous, like on newspaper websites.
Many news sites and blog sites are now requiring people to login to the site as members or use their Facebook profiles to be able to make comments on articles and posts. The interesting aspect here is how the tone, positive or negative, aggressiveness, and civility in comments changes when the individual knows that his or her identity will be known when commenting. This is another layer of text analytics that can open up whole worlds of research data…and will.
