The Watson™ Natural Language Understanding service takes either a body of text or a publicly accessible website that the service can analyze. In this tutorial, we will analyze a news article that is accessible through a URL. You can also choose to analyze other URLs that contain a body of text.
After completing this tutorial, you will be able to:
- Instantiate a Node-RED Starter Kit and a Watson Cloud service (Natural Language Understanding API) on IBM Cloud
- Bind a Watson service to a Node-RED application
- Send a news article URL to the NLU API, and retrieve a table of the response in a table containing the concepts, entities, keywords, categories, sentiment, emotion, relations, and semantic roles
Completing this tutorial should take 45-60 minutes.
Step 1. Create your Node-RED starter app
Follow the steps in this tutorial, “Create a Node-RED starter application.”
Step 2. Add Natural Language Understanding in IBM Cloud
Click the Catalog link in the upper right of the IBM Cloud dashboard. Under the AI section, click the Natural Language Understanding tile.
You can optionally give the service a custom name or leave it as the one given. Click Create.
Click Connections in the menu on the left.
Click Create connection on the right.
Click Connect next to the Node-RED application you created earlier.
IBM Cloud will prompt to restage the application. Click Restage, and the application will restart and include the new service credentials in the environment.
When the application has finished restaging, open the Node-RED Flow Editor. If you already have Node-RED open, refresh the page.
Step 3. Analyze a news article in Node-RED
The Watson Natural Language Understanding service takes either a body of text or a publicly accessible URL to provide content the service can analyze. In this section, we will analyze a news article that is accessible through a URL. You can also choose to analyze other URLs that contain a body of text.
Get the code snippet.
Open a browser tab and visit your application’s endpoint, passing in the URL to the content:
<>with the host of the Node-RED application you chose to name your app.
<>with the URL of the content.
Depending on the content at the URL, you might see a list of attributes, including concepts, entities, keywords, categories, sentiment, emotion, relations, semantic roles, and more mentioned within the text.
To see the JSON representation of the content, insert
format=json in the URL query string.
Finally, return to Step 3 and experiment by disabling some of the features to see how the results change. Try analyzing other URLs and see what results are returned.
This tutorial explained how to analyze a news article that is accessible through a URL. In the tutorial, you learned how to instantiate a Node-RED Starter Kit and a Watson Cloud service on IBM Cloud, bind a Watson service to a Node-RED application, and send a news article URL to the Natural Language Understanding API. Take a look at all of the Watson services and learn how you can use them in your app.