Every pageview event collects default data and enriched data from Maxmind. In addition, if enabled for your project, Permutive collects highly detailed information about the page itself. This data can be used to create segments of users' based on their interests from the content they've read on your site.

We strongly recommend using IBM Watson to classify your pageview data. This enables you to immediately create highly granular, accurate segments of users based on their interests.

Page Context Data

Permutive can collect data about the page through IBM Watson's Alchemy API. 

IBM Watson

IBM Watson’s technology classifies each page using state of the art natural language processing. If you're interested, I recommend trying this  demo of the Alchemy API, which returns a full set of processed results for any given url. 

Permutive collects the following data points from IBM Watson

  • Highly detailed taxonomy data. This is a list of the IAB's Advertising taxonomy. This hierarchical taxonomy has twenty-three main topics and hundreds of sub-topics covering the entire advertising spectrum. 
  • Concepts e.g. 'iPhone, WorldWideWeb'
  • Document Emotion e.g. 'Anger'
  • Document Sentiment e.g. 'Positive'
  • Entities e.g. 'Apple iPhone'

Note: Taxonomy data is collected in the format:
Technology and Computing = '\technology and computing'
Consumer electronics = '\technology and computing\consumer electronics'

Editorial Tags

Permutive can collect additional data on the page from your editorial tags. We usually collect, for example:

  • Categories
  • Sections
  • Tags

Did this answer your question?