Editing the text analyzer rule for the Email channel

The natural language processing (NLP) model for each instance of an Email channel is saved as a text analyzer rule. This model is an advanced feature and is used to analyze the text of the received email for sentiment analysis, text (category) classification, intent analysis, and entity extraction. For example, by using the NLP model defined in the text analyzer rule for the Email channel, you can set up routing conditions so that each received email message is automatically assigned to a user as an interaction case.

Best practices

When you configure the text analyzer rule for an Email channel interface, the following considerations apply:

• To enable natural language processing (NLP) training, you must use model-based classification.
• You must perform document-level classification.
• Classification must fall back to the keyword and rule-based type, if the model-based classification does not return any category with a 70 percent confidence score or higher.

To edit the text analyzer rule:

1. Open an Email channel interface.
2. Click Actions > Open text analyzer.
3. Edit the settings for sentiment analysis, text classification, intent analysis, and entity extraction. For more information, see Text analytics.
4. Click Save.

Open topic with navigation