Definition
Content Classification consists in classifying the content between a predefined set of 370 categories belonging to a 3-level ontology. When it is relevant, the document can be assigned to several categories (ie: Sports & News).
At Linkfluence, we use a 3-level ontology of categories inspired by the IAB Content Taxonomy.
How does it work?
Content Classification is performed based on the content of a document. Thus as mentioned before, the Content Classification is a multilabel classification which means that the content of a document can belong to one or more categories of the ontology.
Note
It would be inaccurate to attempt to classify each document into a single category. As an example, it is highly probable that a long blog post talks about several topics.
Levels of classification
example:
Language coverage
We currently support 13 languages (EN, FR, ES, IT, PT, DE, SV, ZH-CN, ZH-TW, RU, KO, JA, NL)
Applications in Radarly
Content Classification is available in Radarly and the Insight Pages through different widgets such as the Topic Wheel (which is a Sunburst visualisation), barcharts and word clouds.
Screenshot: Insight Page
You have the possibility to filter the widgets by clicking on a category.
Screenshot: Insight Page
You have the possibility to filter the widgets by clicking on a category.
Screenshot: Topic view in Posts & Analytics
This view is displayed after clicking on a topic (here it was society).
💡 Tip
Need more help? Feel free to reach out to us via Live Chat or check out our Customer Community.
Find answers and get help from Meltwater Support and Community Experts.