Training, or Model Training, is the process by which a user teaches Communications Mining what labels and entities apply to verbatims, so that it can apply this understand at scale across the entire dataset.

 

A user trains by manually reviewing verbatims and applying all the labels and entities that are relevant. 

 

Each time a user spends some time reviewing verbatims, it triggers a re-training event where the platform uses the newly reviewed verbatims to improve its understanding of the label concepts and entities.

  

After each re-training event, the model re-reviews all of the unreviewed verbatims in the dataset and updates the predicted labels and entities and their associated confidence scores (and sentiment for labels if label sentiment is enabled).

 

---

Previous: Taxonomies     |     Next: True and false positive and negative predictions