Textbox processes text and performs natural language processing, sentiment analysis and entity and keyword extraction allowing you to build tools that programatically understand the content of text.

Uses for Textbox

This capability has a variety of utilities:

  • Understand if a comment is positive or negative
  • Discover any people mentioned in unstructured data
  • Build email auto-responders that automatically reply with the right answers
  • Extract and handle dates and times (like “yesterday”, or “next Tuesday”)
  • Get a list of the most significant keywords from a series of tweets
  • Analyze customer reviews to discover up and down trends in sentiment

To learn more about what you can do with Textbox, visit the Machine Box blog.


Textbox analyzes a block of text and discovers the following items:

  • Sentences - Each sentence from a body of text is extracted
  • Sentiment - A sentiment value indicates whether a sentence is positive or negative
  • Entities - People, places, organizations, dates and times, etc. for each sentence are extracted
  • Keywords - The most significant items mentioned in the text are returned

Text analyzer tool

Textbox ships with a live text analysis tool that shows you the true power of what can be achieved.

Text analyzer demo preview

To access the Text analyzer:

  1. Sign into the Account page
  2. Setup your MB_KEY variable (learn more about the Box key)
  3. Use the Textbox docker run command provided on the account page
  4. Access http://localhost:8080/demo in your browser

Recently posted on the blog...