Text analyzers in the Facebook channel

Text analyzers process user input and look for matching responses in the Pega Intelligent Virtual Assistant (IVA) for Facebook. As a result, the system knows how to correctly respond.

You can configure one or more text analyzers in IVA for Facebook. They are used together to provide the best responses. The text input from the user is analyzed by the first text analyzer in the list, and if no match is found, the second text analyzer in the list, and so on, until a response is found.

The following text analyzers are available:

• Exact match - The default text analyzer that matches user input to a response exactly.
• Pega NLP - An advanced text analyzer 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, topic, and entity extraction analysis.
• Pega NLP generated (deprecated) - A simplified version of the Pega NLP text analyzer. You can quickly edit or create topics, and expected exact and approximate responses by using NLP. This text analyzer definition is only available in a Facebook channel that was created in previous Pega Platform versions.
• iNLP - An advanced intelligent NLP text analyzer that uses decisioning enabled text analysis. It integrates text analytics with strategies, propositions, and interaction history to provide the context for making better next-best-action decisions. For more information, see the Pega Community Customizable Interaction API for text analytics article.
• Dialogflow - An external natural language processing (NLP) and entity extraction solution from Google. To use the Dialogflow text analyzer for the chatbot, you must first define a Dialogflow agent on the external Dialogflow developer portal and also obtain and install the Dialogflow Text Analyzer component from Pega Exchange. For more information, see the Community Configuring the Dialogflow text analyzer for the Facebook channel article.