Natural Language Processing in CX Index

At the heart of the CX Index solution is the curation of a business’s crucial voice of the customer (VoC) feedback. 

So what’s the next step?

It’s to augment the VoC data with Natural Language Processing (NLP). 

Why use NLP?

NLP lets you

  • take large quantities of unstructured data
  • to analyse it and
  • to understand it

The result?

You can identify ideas for innovation to drive change in your business.

Ideas for innovation that are all around you - in the vast unstructured data-sets you hold.

What is NLP?

Natural language processing (NLP) is a subfield of linguistics, computer science, and artificial intelligence concerned with the interactions between computers and human language.

In particular NLP is how to program computers to process and analyse large amounts of natural language data. (See wikipedia entry for more information).

NLP focuses on how to programme computers to process and analyse large amounts of natural language data. 

It is difficult to perform as the process of reading and understanding languages is far more complex than it seems at first glance. It’s therefore a very technical process.

Structured Data v Unstructured Data

Structured Data

Natural Language Processing (NLP) involves the analysis of what we call unstructured data.

Unstructured data is the opposite of structured data. 

Structured data usually resides in relational databases (RDBMS).

Fields in the RDBMS store length-delineated data e.g.:

  • phone numbers
  • Social Security numbers
  • ZIP codes

Even text strings of variable length like names are contained in records, making it a simple matter to search.

Data may be human- or machine-generated as long as the data comes from within an RDBMS structure.

Unstructured Data

Unstructured data is essentially everything else e.g.

  • Chat
  • IVR
  • Feedback forms
  • Social Media data

Unstructured data:

  • does have internal structure
  • but is not structured via pre-defined data models or schema
  • It may be textual or non-textual, and human- or machine-generated

This format is searchable.  You can search with human generated queries. And also via algorithms. The algorithms use type of data and field names, such as alphabetical or numeric, currency or date.

Data from Social Media posts or Feedback is considered to be unstructured.


Was this article helpful?

Can’t find what you’re looking for?

Our award-winning customer care team is here for you.