Segmenting users using IBM Watson Natural Language Understanding

In this article

Create a segment using the Pageview event, enriched with IBM Watson Natural Language Understanding

All IBM Watson properties can be used in segmentation. 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.

Categories

Example: Segmenting users interested in 'auto parts' (as classified by this standard taxonomy) with a maximum score of 0.8

Screenshot_2020-05-14_at_09.06.34.png

Concepts

Example: Segmenting users interested in 'Gaming' concepts with a minimum score of 0.8

Screenshot_2020-05-14_at_09.14.37.png

Emotions

Example: Segmenting users reading 'joyful' articles with a relevance score more than 0.7 on the topic of 'movies'

Screenshot_2020-05-14_at_09.20.53.png

Entities

Example: Segmenting users reading articles related to 'Spain' with a relevance score of more or equal to 0.8

Screenshot_2020-05-14_at_09.23.45.png

Keywords

Example: Segmenting users interested in articles on 'e-cigarettes' with a minimum relevance score of 0.7

Screenshot_2020-05-14_at_09.25.56.png

Sentiment

Example: Segmenting users reading 'positive' articles with a relevance score more than 0.8

Screenshot_2020-05-14_at_09.27.49.png

 

If you have any questions, please contact customer support by emailing support@permutive.com or chat to the Customer Operations Team via the LiveChat icon in the bottom right corner of your screen.

 

Was this article helpful?
0 out of 0 found this helpful
Have more questions? Submit a request