Leave your label-maker at home
Categorization is arranging, or classifying, content sources such as documents and web pages under a list of topics, or taxonomy. Rosette classification automates this process for your content.
How it works
Rosette analyzes the text in each piece of content to determine the most likely topic in the IAB Tech Lab Content Taxonomy it should belong to, and then assigns it accordingly. For example, it separates the “Business” files from the “Sports” articles, and the “Technology & Computing” websites from the “Science” documents.
Rosette categorization is configured for the IAB Tech Lab Content Taxonomy out of the box.
You can use Rosette for other taxonomies if you like. This requires establishing a training set of documents for the new taxonomy. A training set consists of hand picked examples that best represent each topic in the taxonomy. Rosette is then trained to the new taxonomy so that any future documents can be categorized with accuracy.
Other taxonomies are supported in the on-prem version of Rosette only.