Skip to main content

Out-of-the-box text analytics models

Suggest edit Updated on November 17, 2020

Pega Platform™ provides the following trained and ready-to-use text analytics models:

Model nameText analytics featureLanguageRule nameModel description
Sentiment ModelsTopic detectionEnglish, French, German, Spanish, Italian, Dutch, PortuguesepySentimentModels

Analyzes text to detect sentiment at topic and phrase level.

pySmallTalkTopic detectionEnglish, French, German, Spanish, Italian, Dutch, PortuguesepySmallTalk

Analyzes chatbot content to detect and classify small talk topics, for example, greetings or asking for help.

For more information, see Configure your chatbot for detecting small talk (8.4).

System EntitiesText extractionEnglishpySystemEntities

Analyzes email and chatbot content to detect the following entities: 

  • account_number
  • address
  • amount
  • city
  • country
  • date
  • day_name
  • designation
  • digit
  • email
  • location
  • month_name
  • organization
  • person
  • person_salutation
  • phone
  • SSN
  • time
  • zipcode
  • url
  • us_airport
  • USA_state
  • username
Unit EntitiesText extractionEnglishpyUnits

Analyzes text to detect the following unit entities: 

  • area
  • speed
  • temperature
  • volume
  • weight
  • distance
  • data
  • money
  • percentage
Email ParserText extraction

English, French*, Spanish*

*Available from Pega Platform 8.5


Analyzes email content and detects the following email components:

  • body
  • signature
  • disclaimer
Did you find this content helpful? YesNo

100% found this useful

Have a question? Get answers now.

Visit the Collaboration Center to ask questions, engage in discussions, share ideas, and help others.

Ready to crush complexity?

Experience the benefits of Pega Community when you log in.

We'd prefer it if you saw us at our best. is not optimized for Internet Explorer. For the optimal experience, please use:

Close Deprecation Notice
Contact us