ThingWorx Flow > Connectors Overview > System Connectors > Azure > Text Analytics
  
Text Analytics
Use the Text Analytics action to provide an advanced natural language processing over raw text that includes four main functions—sentiment analysis, key phrase extraction, language detection, and entity recognition.
Using the Text Analytics Action
To use this action in your workflow, connect it to ThingWorx Flow. To connect to the flow, do the following:
1. Drag the Text Analytics action under the Azure connector to the canvas, place the pointer on the action, and then click or double-click the action. The Text Analytics action window opens.
2. Edit the label name, if needed. By default, the label name is same as the action name.
3. To add a new authorization, refer to the section Authorize Azure in the topic Azure connector.
* 
If you previously added an authorization for Azure, select an authorization from the list.
4. Select a Resource Group defined in the subscription.
5. Select the Text Analytics Account from the list.
6. Select a text analytics service:
Detect Language—API returns the detected language and a numeric score between 0 and 1. Scores close to 1 indicate 100% certainty that the identified language is true.
In the Documents section, click Add to enter the Text to process.
Get Recognized Entities—Detect all named entities in the text, such as organizations, people, and locations and so on.
Get Key Phrases—Returns a list of strings denoting the key talking points in the input text.
Sentiment Analysis—API returns a numeric score between 0 and 1. Scores close to 1 indicate positive sentiment and scores close to 0 indicate negative sentiment.
7. In the Documents section, click Add to enter the following details:
Text—Text to process.
Language—The code for the natural language that the document is written in.
Click Add to enter multiple text and language instances.
8. Click Done.
Output Schema
The Text Analytics action returns an output schema as shown in the figure that follows when you select the Sentiment Analysis service: