In this article
Create a cohort using the Pageview event, enriched with IBM Watson Natural Language Understanding
All IBM Watson properties can be used in creating cohorts. If the property is type List of Objects you must state the relevance score (as a decimal) of the property being selected, the relevance score indicates how relevant the property is to the classified document.
Note: When creating a cohort based on Watson data, make sure to add a condition in the cohort builder to exclude the home page and pages with dynamic content. This is because the content on these pages does not reflect the user profile.
Important: This documentation covers our legacy implementation of Watson. For the latest features, setup instructions and best practices, please refer to our new Content Classifications support documentation here. This guide remains live for customers maintaining your current set-up.
Categories
Example: Creating cohorts of users interested in 'auto parts' (as classified by this standard taxonomy) with a maximum score of 0.8
Concepts
Example: Creating cohorts of users interested in 'Gaming' concepts with a minimum score of 0.6
Emotions
Example: Creating cohorts of users reading 'joyful' articles with a relevance score of more than 0.7 on the topic of 'movies'
Entities
Example: Creating cohorts of users reading articles related to 'Spain' with a relevance score of more or equal to 0.8
Keywords
Example: Creating cohorts of users interested in articles on 'e-cigarettes' with a minimum relevance score of 0.7
Sentiment
Example: Creating cohorts of users reading 'positive' articles with a relevance score of more than 0.8
Comments
0 comments
Article is closed for comments.