Train TJBot to Analyze Emotion in Node-RED

Today we’ll train TJBot to analyze emotion using the analyze tone node and the Watson Tone Analyzer service.

We’ll train TJBot to listen to the utterance we want to analyze the emotion of. TJBot can listen and transcribe audio using the IBM Watson Speech to Text service. Create a Watson Speech to Text service and copy the username and password credentials into the Speech to Text section.

TJBot can recognize emotions from text using the IBM Watson Tone Analyzer service. Create a Watson Tone Analyzer service and copy the username and password credentials into the Tone Analyzer section.

Use a function node to find the highest scoring emotion from the response the Tone Analyzer service returns.

When the phrase I like this warm weather is spoken and analyzed, the response is outputted in the debug window.

Here’s a video of how to train TJBot to analyze emotion using the IBM Watson Speech to Text and the IBM Watson Tone Analyzer service.

That’s it for today’s skill. What can you train TJBot to do now that it can understand emotions.

Come back tomorrow and we’ll talk about identifying languages and translating greetings.

This post is part of a series of skills you can train TJBot to perform.