Skip to main content
Sentiment Detection uses AI to analyze the emotional tone of customer messages. When a customer is frustrated, angry, or upset, your team can be alerted immediately.
Sentiment Detection is a Pro feature. Upgrade your plan to access it.

​
How It Works

  1. Customer sends a message
  2. AI analyzes the emotional tone
  3. If a concerning sentiment is detected, staff is notified
  4. Staff can respond appropriately
Example:
Customer: “This is ridiculous! I’ve been waiting 3 days and STILL no response!!” AI detects: Frustrated / Angry Staff gets pinged: “⚠️ Frustrated customer in #ticket-12345”

​
Detected Sentiments

SentimentDescriptionTypical Signs
AngryStrong negative emotionALL CAPS, profanity, threats
FrustratedPersistent dissatisfactionRepeated complaints, exasperation
UpsetGeneral unhappinessDisappointment, sadness
ConfusedUncertainty or misunderstandingQuestions, “I don’t understand”
HappyPositive emotionsThank yous, exclamations of joy
NeutralNo strong emotionFactual statements

​
Getting Started

1

Enable Sentiment Detection

Go to AI Features → Sentiment Detection and toggle it on.
2

Set Up Actions

Configure what happens when each sentiment is detected.
3

Assign Roles

Choose which roles get notified for each sentiment.

​
Tone Actions

For each sentiment, you can configure an action:
ActionDescription
Ping RoleNotify a specific role when detected
Do NothingTrack the sentiment but don’t notify

​
Example Setup

SentimentActionRole
AngryPing Role@Senior Support
FrustratedPing Role@Support Team
UpsetPing Role@Support Team
ConfusedDo Nothing-
HappyDo Nothing-
NeutralDo Nothing-
Only ping for negative sentiments to avoid notification fatigue.

​
Settings

​
Analysis Mode

When to analyze sentiment:
ModeDescriptionBest For
First MessageAnalyze immediatelyQuick detection
First 5 MessagesWait for more contextBetter accuracy
Smart DetectionAI decides timingRecommended
Smart Detection waits if:
  • Staff is actively responding
  • More context would help
  • Message is ambiguous

​
Delay Before Analysis

Seconds to wait before analyzing:
  • 0 - Immediate
  • 15-30 - Let user finish typing
  • 60+ - Wait for multi-message context

​
What AI Looks For

​
Language Signals

SignalSentiment
ALL CAPSAngry/Frustrated
Exclamation marks!!!Strong emotion
Question marks???Confused
Thank you, great!Happy
”I don’t understand”Confused
ProfanityAngry

​
Context Clues

  • Repeated issues → Frustrated
  • Waiting mentions → Frustrated/Upset
  • Threats to leave → Angry
  • Compliments → Happy
  • Neutral facts → Neutral

​
Combination Detection

AI considers multiple signals together: 
"This is the THIRD time I'm asking!!"
     ↓
Repeated issue (frustrated) + CAPS (angry) + !! (strong emotion)
     ↓
Result: Frustrated (primary) + Angry (secondary)

​
How Staff Sees It

When concerning sentiment is detected: 
⚠️ Sentiment Alert: Frustrated Customer

Ticket: #ticket-12345
Customer: John Smith
Sentiment: Frustrated (87% confidence)

"I've been waiting for 3 days with no response"
Staff can:
  • Click to open the ticket
  • See the confidence level
  • Review the triggering message

​
Best Practices

​
Respond Appropriately

When alerted to negative sentiment: Do:
  • Acknowledge their frustration
  • Apologize for the experience
  • Offer a solution quickly
  • Escalate if needed
Don’t:
  • Be defensive
  • Ignore the sentiment
  • Use generic responses
  • Keep them waiting longer

​
Train Your Team

Help staff handle different sentiments:
  • Angry → Stay calm, empathize, escalate if needed
  • Frustrated → Acknowledge, explain, resolve quickly
  • Confused → Clarify, guide step-by-step
  • Upset → Empathize, offer solution

​
Combine with Other Features

Sentiment Detection works well with: Priority Detection: 
Angry + High Priority → Immediate escalation
Auto-Routing: 
Frustrated customers → Senior support
Knowledge Base: 
Adjust AI tone when sentiment is negative

​
Troubleshooting

​
Not Detecting Sentiment

  1. Check if enabled - Verify Sentiment Detection is on
  2. Check analysis mode - “Smart Detection” may wait
  3. Check message content - Very short messages may not have enough signals

​
Wrong Sentiment Detected

  1. Context matters - Sarcasm and irony are hard to detect
  2. Cultural differences - Some expressions vary by culture
  3. Ambiguous messages - Short messages may be misread

​
Too Many Alerts

  1. Adjust actions - Set some sentiments to “Do Nothing”
  2. Increase delay - Wait longer before analyzing
  3. Use Smart Detection - Let AI decide when to alert

​
Missed Angry Customers

  1. Lower sensitivity - Some expressions are subtle
  2. Check action config - Make sure “Angry” has an action
  3. Check role config - Verify the notification role exists

​
Privacy Note

Sentiment Detection analyzes message content to detect emotional tone. It does not:
  • Store sentiment history long-term
  • Share data with third parties
  • Use data for purposes other than detection

Need Help?

Get instant support via private DM