Today we are breaking down some common text analytics related terminology to help you better understand certain terms and how they relate to Customer Experience Management. Let’s start with ‘text analytics’ …

What is text analytics?

Text analytics is the ability to derive meaning and information from text-based sources, such as open-ended comments left in feedback surveys. Text analytics can be used for multiple reasons, but a primary reason to use it in CEM is for sentiment analysis, that is, to understand if an overall comment is either positive or negative. It is difficult and time-consuming to data mine comments one by one, thus having software do this for us automatically, has significant upside.

What is meant by the term natural language processing (NLP)?

Advanced forms of text analytics, typically use something known as natural language processing (NLP). Gartner Research[1] defines NLP as technology that ‘involves the ability to turn text or audio speech into encoded, structured information, based on appropriate ontology.’ NLP basically lets us understand hundreds of comments within minutes, alleviating manual data mining required to go through each and every comment one by one to decipher its meaning or sentiment.

What is machine learning?

This is another term that is typically used to describe more advanced forms of text analytics. Here, algorithms are used in conjunction with other technologies such as NLP and are guided by lessons from existing information or data, without the need to be explicitly programmed (Gartner, 2017[2]).

Text Analytics is also referred to as ‘unstructured data analysis’, and ‘verbatim analysis’. To learn more about text analytics, stay tuned this month for some upcoming posts on the topic! For now, read our Monthly Must Reads feature where we outline some great reads on text analytics online from Temkin, and Forrester.


[1] Gartner Research, IT Glossary, Retrieved on 6 Feb 17 from:

[2] Gartner Research, IT Glossary, Retrieved on 6 Feb 17 from: