24

Text capture

What is it?

If you want to run any type of text-based analytics then clearly you need text to analyse. In most businesses there is already a vast amount of text data available that could be analysed although it will need to be captured in a form that can then be used. This always means electronically and where the text is datafied rather than just digitised.

If you were to scan a text document, you have effectively created an electronic image of the document which means the document is digitised as a soft copy but it is not datafied. You couldn’t search that scanned document for a phrase or run any analysis on the text because each word is not stored separately as text, rather it is stored as a single image file. This means ...

Get Key Business Analytics now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.