Configuring topic detection

Identify the Taxonomy rule to apply on the text data that you want to analyze. Detecting topics (talking points) to which various units of text are assigned can help you automatically classify user queries and shorten customer service response times.

  1. In the navigation panel, click Records > Decision > Text Analyzer.
  2. Open the Text Analyzer rule that you want to edit.
  3. In the Text categorization section, select the Enable topic detection check box.
  4. In the Taxonomy field, press the Down Arrow key to specify the Taxonomy that you want to use for categorization analysis.
    The Taxonomy rule contains taxonomies for all supported languages. The rule can also contain categorization machine learning models that you trained in the Prediction Studio.The following Taxonomy rules are available by default:
    • pyBankingTaxonomy
    • pyCustomerSupportTaxonomy
    • pyTelecomTaxonomy
  5. Select the topic preference by enabling one of the following options:
    • Exclude any categorization models from analysis by selecting Always use rule based topics. Select this option when no categorization model is associated with the taxonomy rule or when the keywords-based categorization analysis provides more reliable results than the model.
      Note: To check whether the Taxonomy rule is associated with a categorization model, click the Open icon next to the Taxonomy rule.
    • Select Use model based topics if available to include the categorization model from the Taxonomy rule in the analysis if available.
  6. Optional: Configure language detection preferences.
    Perform this step to analyze content that is in more than one language and configure your application to always detect the specified language For more information, see Configuring language detection preferences.
  7. Optional: Increase topic detection accuracy by enabling checking spelling.
    For more information, see Configuring spelling checker settings.
    Important: If you enable the spelling checker, you might experience increased memory consumption in your application.
  8. Click Save.