How do I view Conversation Sentiment? \[BETA\]
Required Feature Flags
The following feature flags and permissions are required to use this feature:
Feature Flag | Technical Name | Description |
Sentiment Analysis (BETA) |
| Enables AI-powered sentiment detection on transcribed calls and tickets. Currently in BETA — contact your customer success manager or support to have it enabled |
Required Permissions:
View Sentiment Results — to see sentiment indicators and the Insights tab on imported contacts and evaluations. By default this is enabled for all users other than agents
Sentiment Analytics — \[BETA\]
Good to Know
We offer Sentiment Analysis across all transcribed calls and tickets, with more functionality (such as the ability to filter by sentiment) coming in future releases.
The feature is in BETA — please contact your customer success manager or our support team if you would like it enabled on your account.
Once turned on, all conversations from that date will be analysed. The feature can be switched off via a support request too.
Viewing Sentiment Results
Providing you have the permission to view sentiment results, you will see additional information when viewing an imported contact or evaluation. We highlight:
Parts of the conversation with positive sentiment (Green Face)
Parts of the conversation with negative sentiment (Red Face)
Prolonged periods of negativity or positivity when identified (within the new "Insights" tab)
Responses that are neutral (neither positive nor negative) are still analysed but are hidden to avoid cluttering your conversation thread.
Who Can See Sentiment Results?
The permission to View Sentiment Results can be controlled within Roles and Permissions. By default, all users other than agents have the permission enabled. This means the Sentiment Results and Insights tab are visible when:
Viewing an imported contact
Viewing an evaluation
Viewing a completed evaluation
What's Next?
This BETA is just our first step towards AI-fuelled insight, which we'd love your feedback on.
In the near future, we plan to extend the functionality of this BETA, including:
Presenting an overall sentiment score for the conversation from both the perspective of the customer and the agent
Enabling you to filter (and therefore trigger Auto Work Queues) based on Sentiment Results
The ability to configure the sensitivity of Sentiment Results
Identifying significant shifts in sentiment throughout the length of a conversation (e.g. an agent doing a great job of turning a conversation around)