My General Topic Classification Model — From Labelling to Deployment

Author(s): Wee Tee Soh

Originally published on Towards AI.

Bird with coloured balls — AI-generated image

During the course of my work in NLP, I often find a need to do initial filtering of massive numbers of documents or texts in order to remove the noise from the gold that I want. For a start, I could categorize them into well-defined general topics (e.g., food, finance, sports, etc.) using a topic classifier. Specifically, into one of the following 16 broad topics:

entertainment & musichealthbusiness & financesportsreligionpets & animalsfamily & relationshipsfoodtraveleducation & referencepolitics & governmentsociety & culturemundanecomputers & internetscience & mathematicsothers

After which, I can then focus on a particular topic(s) of interest… Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI