Summary: ◀▼
You can view and update intelligent triage classifications in tickets to get more context on the customer’s request. See the ticket’s topic, language, and sentiment, along with confidence levels, in the ticket fields or header, then adjust them if needed. You can also review topic and sentiment update history in ticket events. This helps you handle tickets with better context and accurate triage.
From within a ticket, you can see the ticket's topic, language, and sentiment classifications. This information comes from intelligent triage and gives you additional context about the ticket to help you resolve the customer's request more quickly.
This article contains the following topics:
- Viewing and updating intelligent triage classifications in tickets
- Viewing and updating a ticket's topic and sentiment in the ticket header
- Viewing a ticket's topic and sentiment update history
Related articles:
Viewing and updating intelligent triage classifications in tickets
The ticket properties panel within a ticket shows the intelligent triage classifications. From here, you can change a ticket's topic, language, or sentiment if the original classification isn't accurate.
To view intelligent triage classifications within a ticket
- In the Agent Workspace, open any ticket.
- In the ticket properties panel on the left, view the following ticket
fields:
- Topic and Topic confidence: A classification of what the customer is asking about and how likely the classification is correct. Confidence is either High, Medium, or Low.
- Language and Language confidence: A classification of the language the ticket is written in and how likely the classification is correct. Confidence is either High, Medium, or Low.
-
Sentiment and Sentiment confidence: A classification of how
the customer feels about their request and how likely the
classification is correct. Confidence values include:
- Very positive: The message likely contains strong positive words (like "brilliant" or "perfect"), positive words modified by intensity adverbs, or multiple positive sentences.
- Positive: The message likely contains phrases expressing gratitude, or one to two positive sentences.
- Neutral: The message likely contains factual statements without additional negative quantifiers (like "any" or "always"), or a mix of positive and negative statements.
- Negative: The message likely contains phrases expressing frustration, complaints containing negative words, or repetition of the same dissatisfaction.
- Very negative: The message likely contains strong negative words, capitalized text, multiple exclamation marks, or multiple negative phrases.
- (Optional) To change any of the values, click the appropriate field and
select a new value from the drop-down list.
Most intelligent triage classifications are based on a ticket's first message only. Any updates you make to these fields should still be based on the first message. Additionally, updating these fields doesn't train the machine learning model responsible for intelligent triage.
If configured by an admin, the topic and sentiment classifications update based on the latest message from the end user. You can make updates based on their latest message.
Viewing and updating a ticket's topic and sentiment in the ticket header
If configured by an admin, you can also view the topic and sentiment in the ticket header.
To view a ticket's topic and sentiment
- In the Agent Workspace, open any ticket.
- In the ticket header, view the topic and sentiment.
You can hover over it to see the full text if necessary.
- (Optional) To change the topic or sentiment, click the current value and
select a new value from the drop-down list.
Viewing a ticket's topic and sentiment update history
You can view a ticket's topic and sentiment update history from the ticket's events.
- In the Agent Workspace, open any ticket.
- Click the events icon (
) in the conversation header.If there have been updates to the ticket's topic or sentiment, the events display the system update with the previous topic or sentiment and the new topic or sentiment, after the end user last commented.
