You can now increase the accuracy of text analytics models in pre-production environments by updating them with new data, for example, with feedback data that you collect. With this feature, you can achieve a better understanding of your customers' needs, which helps you retain and grow your customer base.
Migrating models and feedback data
To improve the management of the text analytics models in your application, use model versions. For example, you can switch back to a previous model version if the new version does not meet your business requirements.
You can further increase the model's accuracy by adding more training data to an existing text analytics model. Edit the training data that is available in the system, for example, to recover from errors.
Consult the following diagram to learn about how you can use text analytics model migration and versioning to update the model with feedback data:
Clearing feedback data
The system does not clear the feedback data upon export. As a best practice, after you complete the model update cycle, using the feedback data that you exported from the production environment, clear the feedback data from the production environment. By clearing the feedback data, you can start collecting new feedback for the next version of the model and you ensure that the next time you export feedback data, the data does not include the feedback that you used to train the previous version of the model.
You can clear feedback data for a model by clicking Actions > Clear feedback data.
For more information about updating text analytics models, see Updating training data for text analytics models.