Skip to content

Generative AI & LLMs

Text classification

Assigning labels or categories to written content using rules or learned patterns.

Example

A system routes messages into billing, delivery or product-support categories.

Why people use it

It helps organize messages or documents for the next step.

What you'll hear

“Send these complaints to the right department.”

What this means for you

Check whether the category scheme matches the way people use the information.

Can you control it?

Developer-only

The people building or running the AI choose this setup. An everyday user generally needs their help to change how this part works.

Common questions

Can one message receive several labels?
Yes, if the tool allows it. A message might concern both a delivery problem and a refund.
Can categories overlap?
Yes. A message may concern both billing and delivery, even when the system is allowed only one label.
Do short messages make classification harder?
They can. A few words may leave too little background information to choose the intended category.

Related terms

Still have questions?

Up to 500 characters.

Ask LATHIC about AI. Relevant glossary entries may be included.

Your question, the glossary entries it matches, and a rotating pseudonymous identifier go to Microsoft Azure’s OpenAI service through Vercel AI Gateway to generate an answer. Zero retention and no training are required of the provider, and LATHIC does not save your question or answer. Privacy Notice