Classifiers > Labels > Policies

<aside> 💡

Microsoft Purview provides three ways of identifying items so that they can be classified:

1. Manually by users
2. Automated pattern recognition, like sensitive information types (SITs)
   1. Built-in sensitive information types**:** These built-in SITs cover commonly recognized sensitive information types, such as social security numbers, credit card numbers, and email addresses. While these SITs can't be edited, they can serve as templates for creating custom sensitive information types.
   2. Named entity sensitive information types**:** Named entity SITs automatically identify specific types of named entities, such as person names, physical addresses, or medical terms and conditions. These SITs are also predefined and can't be edited or copied.
   3. Custom sensitive information types**:** If the preconfigured sensitive information types don't meet your needs, you can create your own custom SITs that you fully define. You can also copy one of the preconfigured SITs and modify it.
   4. Exact data match sensitive information types**:** EDM-based SITs are built from scratch. EDM-based classification enables you to create custom sensitive information types that refer to exact values in a database of sensitive information.
3. Machine learning (trainable classifiers) </aside>

• Data classification overview
• Classify data using sensitive information types (SITs)
• Classify data using machine learning (trainable classifiers)

Purview - Data Classification Tabs

• Overview Tab: Review sensitive information and label usage
• Content explorer Tab: Explore labeled and sensitive content
• Activity explorer Tab: Understand activities related to your data