Using the Sentiment Analysis Add On you can keep a pulse on the customers sentiment when they interact with your conversation flows. At points where customers are frustrated you can use the sentiment score to navigate customers to a faster resolution path such as getting them connected to an agent.
How to use Sentiment Analysis Add On
You can find the Sentiment Analysis Add On in the nodes on the left hand side of your flow builder.
You can drag the node and add connect it to any node after which you would like to understand the customer sentiment.
For the sentiment analysis you will need to use a text field where you have captured customer input or a parameter where you have stored the transcript.
You can specify these in the settings.
Once the sentiment analysis is done the conversation moves to the next node and adds actionOutput as a parameter.
The actionOutput parameter will have the following value format.
{"magnitude": 0.8, "score": 0.8}
| Magnitude | This value represents the amount of emotional content in the text. Higher the value the more emotional content. |
| Score | Score is a measure of the positive sentiment. 0.0 represents a neutral sentiment. |
You can now use these values in subsequent conditional rules to make decisions such as routing a frustrated customer to an agent.
Sentiment varies for different use cases and customers. You might find differing results for your specific scenario, hence using the score you can decide thresholds that suite your use case.