Configuring preprocessing models in text predictions
To identify the body, disclaimer, and signature components of emails in an email channel, you can configure a preprocessing model in the text prediction, for example, the default pxEmailParser rule. You can choose what type of analysis to perform on each email component, depending on your business needs.
Open the text prediction:
In the navigation pane of App Studio, click Channels.
In the Current channel interfaces section, click the icon that represents a channel for which you want to configure the text prediction.
On the channel configuration page, click the Behavior tab, and then click Open text prediction.
In the Prediction workspace, click the Settings tab, and scroll down to the Preprocessing model section.
In the Model field, select the preprocessing model that you want to use to parse email text.The default text analytics rule that is available in this field is pxEmailParser. This email parser supports several languages. For more information, see Out-of-the-box text analytics models.
In the Datatype field, specify the content that you want to analyze:
- To analyze the email without attachments, select Body.
- To analyze the attachments, select Attachment.
- To analyze both the email and the attached text, select All.
In the Email section analysis section, select what type of analysis to perform on each email component, depending on your business needs.The email parser analyzes the email content (body, attachment, or both) and detects the following email components:
You can choose to perform topic and sentiment analysis on the body of your emails, and entity detection on the body and signature.
- The main message of an email.
- A section that holds a legal notice or warning, for example, a copyright or confidentiality disclaimer.
- A section that is added at the end of the email, typically with contact information or a quote.