Watson Natural Language Understanding

The Qlik Watson Natural Language Understanding Connector allows you to analyze semantic features of text and import the analysis data directly into your QlikView and Qlik Sense applications.


The Qlik Web Connectors help you connect to different data sources and fetch data in the same way. Learn how to authenticate a data source connection and how to use tables to fetch data.

Connecting to data sources

Ways to access your data

To use the Qlik Watson Connector, use your relevant Watson credentials with which to authenticate the connector.

After authenticating the connector a number of tables are available:

  • Categories - Lists the top three Categories, used to categorize content. Visit the Categories Hierarchy page for the complete list.
  • Concepts - Lists the Concepts that are detected in the text analysis.
  • Emotions - Lists the Emotions that are detected in the text analysis.
  • Entities - Lists the Entities that are detected in the text analysis, with connected Emotion and Sentiment analysis.
  • Keywords - Lists the Keywords that are detected in the text analysis, with connected Emotion and Sentiment analysis.
  • Metadata - Returns available metadata for the HTML or URL.
  • SemanticRoles - Parses the text content into subject/action/object.
  • Sentiment - Analyzes the Sentiment of the text content.

For further information, see:


Error message: "Too many requests"

Possible cause  

You have exceeded the usage limits on concurrent API requests. The default limit is 30 concurrent requests, but this limit may decrease when the service is experiencing heavy traffic.

Proposed action  

To reduce the impact of reaching the API rate limits, develop your app with the following in mind:

  • Extract only the data you need.
  • Reload one Watson-based application at a time.
  • Ensure that loops in your script that make API calls will not result in infinite loops.

Did this information help you?

Thanks for letting us know. Is there anything you'd like to tell us about this topic?

Can you tell us why it did not help you and how we can improve it?