Defining Facebook text analyzer topics

The Facebook chatbot configuration for a Pega Intelligent Virtual Assistant (IVA) includes text analyzer topics that are based on natural language processing (NLP) and decisioning enabled text analysis. Defining topics in the Facebook configuration allows the chatbot to determine the best response based on user input.

Note: To use Pega Intelligent Virtual Assistant for Facebook in your application, you must obtain and install the Facebook channel component from Pega Exchange.
  1. Edit a Facebook channel interface and click the Behavior tab.
  2. In the Text Analyzer section, click Edit topics.
  3. Click + Add topic.
  4. Complete the following fields:
    • Topic - Required. The natural language processing topic for the chatbot to use as the response based on its must match, approximate match, and never match criteria.
    • Approximate match - Optional. The comma-separated words or phrases to use as an approximate match for the chatbot content for the topic. For example, for an initial greeting response, you can specify: 'hello' or 'good morning'.
    • Must match - Optional. The comma-separated words or phrases to use as an exact match for the chatbot content for the topic. For example, for an initial greeting response, you can specify 'hi'.
    • Never match - Optional. The comma-separated words or phrases to never match for the chatbot content for the topic. For example, for an initial greeting response, you can specify 'bye'.
  5. Repeat steps 3 and 4 to add additional topics.
  6. Click Submit.