Document classification is a good example of Machine Learning in the form of Natural Language Processing. It is a worth your attention process that would reduce time of searching and retrieving essential data. It quickly separates important information from insignificant text.

The process of assigning documents to categories is based on pre-trained data models. Our text2data tool detects documents in 26 categories - we call it "auto-categories".

We also provide our users with the ability to train their own document categorization models, the analysis results based on such a user pre-trained models are displayed separately - we call it "user categories".


Following auto categories are being detected [IAB QAG taxonomy]

IAB code Category name
IAB2 Automotive
IAB1-1 Books and Literature
IAB13-3 Business and Finance
IAB1-3 Fine Art
IAB8 Food & Drink
IAB7-35 Healthy Living/ Children's Health
IAB9-2 Hobbies & Interests/ Arts & Crafts
IAB9-16 Hobbies & Interests/ Musical Instruments
IAB10 Home & Garden
IAB20-18 Hotels and Motels
IAB7 Medical Health
IAB1-5 Movies
IAB1-6 Music
IAB12 News and Politics
IAB13-2 Personal Finance/ Personal Debt/ Credit Cards
IAB16 Pets/ Pet Supplies
IAB15 Science
IAB22 Shopping/ Children's Games & Toys
IAB22-2 Shopping/ Gifts & Greetings Cards
IAB17 Sports
IAB18 Style & fashion
IAB18-1 Beauty
IAB3-4 Technology & Computing/ Computing/ Computer Software & Applications
IAB19 Technology & Computing/ Consumer Electronics
IAB19-6 Smartphones
IAB9-30 Video Gaming

Please choose one of the options to start!

Excel addin menu Google Sheets Add-on