Facebook channel configuration

To provide a better user experience for a conversational Facebook chatbot, you can configure its behavior to fit the needs of your organization. You can configure the predefined system responses, a list of text analyzer definitions, and the interaction time-out for a Facebook chatbot that is used as a Pega Intelligent Virtual Assistant.

Note: You must purchase a separate license before using Pega Intelligent Virtual Assistant in your application. You must also obtain and install the Facebook channel component from Pega Exchange.

System responses

You can customize system responses for standard events that happen during an interaction between a user and the chatbot application. You can define additional custom responses when configuring the content for the chatbot.

  • Welcome - Displays a welcome message to the user of the chatbot on their first interaction with the channel.
  • No match - Displays a warning that no matching command was found based on the user input.
  • Multiple matches - Displays a stating that multiple commands matched the user input.
  • Internal error - Displays a message that a system error occurred for the chatbot.
  • Authentication - Displays a message prompting a user to authenticate.
  • Authentication-Success - Displays a success message immediately after a user has successfully authenticated.
  • Authentication-Fail - Displays a failure message immediately after a user has failed to authenticate.

Text analyzer

A Facebook chatbot analyzes user input to determine a response by using one or more text analyzer definitions:

  • Exact match - The default text analyzer that matches user input to a response exactly.
  • Pega NLP generated - A simplified version of the Pega NLP text analyzer. You can quickly edit or create categories, and expected exact and approximate responses by using the natural language processing (NLP) capability.
  • Pega NLP - An advanced feature that uses the best approximate match by using advanced natural language processing (NLP) and artificial intelligence. You must specify a text analyzer rule for this definition type indicating sentiment, classification, category, and entity extraction analysis.

You can specify several text analyzer definitions. They are used together to provide the best responses. The text input from the user is analyzed by the first text analyzer definition in the list, and if no match is found, the second text analyzer definition in the list, and so on, until a response is found.

Note: You can also specify third-party text analyzers for the Facebook chatbot. You must install an additional component from Pega Exchange.

Interaction timeout

You can enable interaction time-out and define the number of minutes of inactivity after which the Facebook chatbot times out of the user session.

Options

You can configure the chatbot to initiate the interaction by displaying the Get Started button and an initial greeting message to the user of the Facebook chatbot.