Providing feedback through an API
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:
- 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:
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