14.5 Text Classification

Text classification assigns a category label to a piece of text. Sentiment analysis is one example, but the idea is broader: sorting emails into 'spam' or 'not spam', routing support tickets to the right department, or tagging news articles by topic. The model learns from labeled examples and predicts labels for new text.

A government service portal in Ethiopia receives citizen messages in Amharic. A classifier can automatically sort each one — 'health', 'taxes', 'roads', 'education' — and route it to the correct office, saving staff hours of manual sorting.