Skip to main content


         This documentation site is for previous versions. Visit our new documentation site for current releases.      
 

Providing feedback through an API

Updated on May 17, 2024

Create a feedback loop for your models by using the pxCaptureTAFeedback activity.

Through this activity, you can manually correct unexpected or inaccurate text analysis outcomes, for example, by updating sentiment value from positive to negative or changing the assigned topic. You can then update the model that performed the analysis by feeding it the corrected outcomes.

Categorization models

For categorization models, provide your feedback in the ActualResult field. The actual result can be a sentiment value (for example, Negative), an intent type (for example, Complaint), or topic assignment (for example, Customer Support > Phone).

See the following example for reference:

Providing feedback to categorization models through testing
Examples of parameter values for providing feedback to categorization models
  • To submit the record for a review before the model includes it as feedback, select the Mark For Review checkbox.
  • To exclude the record from being included as feedback to the model, select the Is Test checkbox.

Text extraction

For text extraction, provide your feedback in the form of annotated text in the Text field, for example, <START:PERSON> John <END> works at <START:ORGANIZATION> Pegasystems <END>. He lives in <START:LOCATION> Boston <END>.

See the following example for reference:

Providing feedback to text extraction models through testing
Examples of parameter values for providing feedback to text extraction models.

While entering your feedback in the Text field, you must preserve all correct annotations. Otherwise, the model treats all removed annotations as negative feedback.

  • Previous topic Providing feedback to text analytics models
  • Next topic Feeding the feedback data to text analytics models

Have a question? Get answers now.

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

Did you find this content helpful?

Want to help us improve this content?

We'd prefer it if you saw us at our best.

Pega.com is not optimized for Internet Explorer. For the optimal experience, please use:

Close Deprecation Notice
Contact us