QuestionQ25

Communications Mining

What is one recommended best-practice rule when creating a UiPath Communications Mining label taxonomy?

  • A Create some non-value-adding labels (e. g. out of office emails, thank you emails) to indicate to the platform what is or isn't important to analyze.
  • B Create labels based on the model version to indicate that the platform ensures synchronization.
  • C Create a large set of labels in the taxonomy, then focus the training of the model on a subset to reduce training time.
  • D Create specific labels with a degree of overlap to ensure 100% coverage.
Explanation

A Communications Mining taxonomy should include some uninformative, non-value-adding labels, such as thank-you or out-of-office emails, so the platform can distinguish content that is important to analyze from content that is not. Labels should also be specific and non-overlapping.

Learn more

Community Discussion

No comments yet. Be the first to start the discussion!