Enabling the NLP model training for the Facebook channel

When you update the natural language processing (NLP) model for a configured Facebook channel interface, you train the channel to make better predictions about the content of the chat conversation in relation to sentiment analysis, text (topic) classification, intent analysis, and entity extraction. You can enable this capability for each configured Facebook channel interface.

Before you begin: 

To use Pega Intelligent Virtual Assistant for Facebook in your application, you must obtain and install the Facebook channel component from Pega Exchange.

You update the NLP model for a channel by reviewing record items that were saved by Pega Intelligent Virtual Assistant.

  1. Open a Facebook channel interface. For more information, see Configuring the Facebook channel.
  2. Click the Behavior tab.
  3. In the Text Analyzer section, select the Enable model training check box.
  4. Click Save.