Skip to main content


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

Updating training data for text analytics models

Updated on May 17, 2024

Increase the accuracy of your text analytics models by adding feedback data and providing additional training data.

Note: This procedure causes the system to retrain your model. Depending on the model size, retraining the model might be a lengthy process.
Before you begin: Create a ruleset version on which you want to base your text analytics model version. Select a ruleset version that is higher than the current model version.
  1. In the navigation pane of Prediction Studio, click Models.
  2. For the model for which you want to edit the training data, click the More icon.
  3. In the More list, select Update, and then select the model language version.
  4. In the Update language window, configure the settings for the new model version:
    1. Select the Do you want to change version? check box.
    2. In the Ruleset version list, select a ruleset version on which you want to base your text analytics model version.
    3. Click Update.
  5. Confirm the model configuration:
    • For topic models, in the Taxonomy selection step, click Next.
    • For intent and sentiment analysis models, in the Lexicon selection step, click Next.
  6. In the Source selection step, update the training data:
    ChoicesActions
    Add feedback data to the model
    1. In the Feedback data section, select the Include recorded feedback check box.
    2. Click Next.
    Make changes to the current training data
    1. In the Existing data source section, download a file that contains the current training data by clicking its name.
    2. In your local directory, open the training data file, and then make the necessary changes.
    3. Save the training data file to your local directory.
    4. In Prediction Studio, in the Existing data source section, click Upload data source.
    5. In the Upload data source window, click Choose file, and then select the file that includes your edits.
    6. Select the Overwrite the existing data check box, and then click Upload.
    7. Optional: To add feedback data to the model, in the Feedback data section, select the Include recorded feedback check box.
    8. Click Next.
    Add more training data to the model
    1. In the Existing data source section, click Upload data source.
    2. In the Upload data source window, click Choose file, and then select a .csv file that contains the training data that you want to add.
    3. In the Upload data source window, select the Append to the existing data check box, and then click Upload.
    4. Optional: To add feedback data to the model, in the Feedback data section, select the Include recorded feedback check box.
    5. Click Next.
  7. In the Sample construction step, click Next.
  8. In the Model creation step, click Next.
    Result: The system retrains the model based on the data that you provided.
  9. In the Analysis step, click Next.
  10. In the Model selection step, click Update language name.
Result: The system creates an updated version of the model on top of the old version.
What to do next: If you retrained the model by using feedback data that you exported from the production environment, it is essential to clear the feedback data in the production environment. By clearing the old feedback, you ensure that the data is not used in the next model development cycle. For more information, see Clearing feedback data for 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