1.On the Models page, click the New Model button to add a new model.

2. In the Create a new model wizard that appears, click the model you want to use and then click Next.

3. On the second page of the wizard, select the data stream to train with the model and click Next.

You can optionally add a filter before clicking Next. For more information on filters, see Filter and segment data.

4. On the third page of the wizard, under Unassigned Fields, find a field to use as the ground truth for the model, click the + next to it, and select Ground Truth. In this example, Glassdoor provides an overall field that we can use for this purpose.

A ground truth is a field that the user provides to rate their overall feeling, such as a numerical or star rating. The model compares the ground truth with the words it finds in the unstructured text or training feature, and extrapolates this information to predict sentiment in new data.

The field moves to the Assigned Fields column.

5. In the Unassigned Fields column, select the free-form text or structured data field to use for training, click the + next to it, and select Unstructured Text. In this example, Glassdoor provides a content field that combines all of the free-form text fields into one.


Supervised models require one Ground Truth field and at least one Unstructured Text or Training Feature field.

  • Ground truth: a field that objectively measures how the user feels, such as a star rating.
  • Unstructured text: a field that collects free-form user feedback, that is, they type it rather than select from a list.
  • Training feature: a field that collects structured user data, that is, data that is numerical or that is selected from options .

6. The field is added to the list of Assigned Fields. At the top of the Assigned Fields column, a green "Looks good" message lets you know when you have selected the correct fields for the model type. Click Next to continue.

7. Optionally click Advanced to reveal more settings.

Some of these settings are common to all models, and some are specific to each model. See Advanced settings in the article for your model for details.

8. On the Complete & Submit page of the wizard, add a name, and optionally add tags and a description. These fields appear in the tile for the model once it is submitted.

9. Click Submit to begin training on the model. The following message appears. When the model is ready, the message disappears and the model is added to the Models page.

Did this answer your question?