GETTING STARTED
Kore.ai XO Platform
Virtual Assistants Overview
Natural Language Processing (NLP)
Concepts and Terminology
Quick Start Guide
Accessing the Platform
Working with the Builder
Building a Virtual Assistant
Using Workspaces
Release Notes
Current Version
Previous Versions
Deprecations

CONCEPTS
Design
Storyboard
Dialog Tasks
Overview
Dialog Builder
Node Types
Intent Node
Dialog Node
Entity Node
Form Node
Confirmation Node
Message Nodes
Logic Node
Bot Action Node
Service Node
Webhook Node
Script Node
Group Node
Agent Transfer
User Prompts
Voice Call Properties
Dialog Task Management
Connections & Transitions
Component Transition
Context Object
Event Handlers
Knowledge Graph
Introduction
Knowledge Extraction
Build Knowledge Graph
Add Knowledge Graph to Bot
Create the Graph
Build Knowledge Graph
Add FAQs
Run a Task
Build FAQs from an Existing Source
Traits, Synonyms, and Stop Words
Manage Variable Namespaces
Update
Move Question and Answers Between Nodes
Edit and Delete Terms
Edit Questions and Responses
Knowledge Graph Training
Knowledge Graph Analysis
Knowledge Graph Import and Export
Importing Knowledge Graph
Exporting Knowledge Graph
Creating a Knowledge Graph
From a CSV File
From a JSON file
Auto-Generate Knowledge Graph
Alert Tasks
Small Talk
Digital Skills
Digital Forms
Views
Introduction
Panels
Widgets
Train
Introduction
ML Engine
Introduction
Model Validation
FM Engine
KG Engine
Traits Engine
Ranking and Resolver
NLP Configurations
NLP Guidelines
Intelligence
Introduction
Contextual Memory
Contextual Intents
Interruption Management
Multi-intent Detection
Amending Entities
Default Conversations
Sentinment Management
Tone Analysis
Test & Debug
Talk to Bot
Utterence Testing
Batch Testing
Conversation Testing
Deploy
Channels
Publish
Analyze
Introduction
Conversations Dashboard
Performance Dashboard
Custom Dashboards
Introduction
Meta Tags
Dashboards and Widgets
Conversation Flows
NLP Metrics
Containment Metrics
Usage Metrics
Smart Bots
Universal Bots
Introduction
Universal Bot Definition
Universal Bot Creation
Training a Universal Bot
Universal Bot Customizations
Enabling Languages
Store
Manage Assistant
Plan & Usage
Overview
Usage Plans
Support Plans
Invoices
Authorization
Multilingual Virtual Assistants
Masking PII Details
Variables
IVR Settings
General Settings
Assistant Management
Data Table
Table Views
App Definitions
Sharing Data Tables or Views

HOW TOs
Build a Flight Status Assistant
Design Conversation Skills
Create a Sample Banking Assistant
Create a Transfer Funds Task
Create a Update Balance Task
Create a Knowledge Graph
Set Up a Smart Alert
Design Digital Skills
Configure Digital Forms
Configure Digital Views
Add Data to Data Tables
Update Data in Data Tables
Add Data from Digital Forms
Train the Assistant
Use Traits
Use Patterns for Intents & Entities
Manage Context Switching
Deploy the Assistant
Configure an Agent Transfer
Use Assistant Functions
Use Content Variables
Use Global Variables
Web SDK Tutorial
Widget SDK Tutorial
Analyze the Assistant
Create a Custom Dashboard
Use Custom Meta Tags in Filters

APIs & SDKs
API Reference
API Introduction
API List
API Collection
koreUtil Libraries
SDK Reference
SDK Introduction
SDK Security
SDK Registration
Web Socket Connect and RTM
Using the BotKit SDK

ADMINISTRATION
Introduction
Assistant Admin Console
Administration Dashboard
User Management
Add Users
Manage Groups
Manage Roles
Assistant Management
Enrollment
Invite Users
Send Bulk Invites
Import User Data
Synchronize Users from AD
Security & Compliance
Using Single-Sign On
Security Settings
Cloud Connector
Analytics
Billing
  1. Home
  2. Docs
  3. Virtual Assistants
  4. Advanced Topics
  5. Sentiment Management

Sentiment Management

Emotion tones are critical indicators in understanding the attitudes and opinions of users interacting with the bots. Sentiment Management allows the developer to define and trigger events based on the user’s emotion or sentiment.

Notes

  • This feature was introduced in v7.0.
  • This feature is not supported in all languages. Click here for details.

Negative emotion scenarios like anger or disgust are typically considered for transferring the conversation to a live agent.

The Natural Language Processing (NLP) interpreter can parse user utterances for specific words and phrases, and then provide an average tone score based on the connotation, word placement, and any added modifiers. (Click here for more on Tone Analysis)

The tone or sentiment scores are stored as context and used to drive the flow of a dialog task through conditional transition statements. You can use these scores to steer user-bot conversations or seamlessly invoke escalation to a live agent.

Configuration

You can define multiple sentiment events from Natural Language > Intelligence.

Use New Event to define an event to capture the user’s emotion.

Following parameters can be configured for a sentiment event:

  • Event Name – Name of the event.
  • Event Trigger – Defines how often the sentiment must be checked. It can be set to:
    • On Task Completion – Sentiment is checked only after completion of a task (dialog, action, alert, and information task).
    • After Every User Message – Sentiment is checked after every message from the end-user. The event is evaluated before proceeding with the conversation using the incoming utterance.
  • Emotion Configurations
    • Select the required emotions to be captured from a list of six tones, angry, disgust, fear, sad, joy, and positive.
    • Select if the tone should be considered at the Session level or Message level
      • Session-level tone value is a consolidated tone value across all user messages in a conversation session.
      • Message-level tone value is a tone value calculated for a given message from the user.
    • Define the range to be considered for each of these tones, the range can be between -3 to +3. (Click here for more on Tone Analysis)
    • When multiple emotions are selected, the event is triggered when ALL the tone rules are met. In case you want the event to trigger when any tone rule is met, add them as separate rules.
      Post v8.1, the platform can identify the emojis in user utterance and set the tone accordingly.
    • Event Configuration – The result of the event trigger could be either to Run a Dialog or Run a Script.

Event Flow

Emotion tones are continuously updated whenever a message received from the users and as such the sentiment events are also continuously evaluated. When an event’s criteria are met, the platform triggers the defined behavior.

  • If the configuration used is to Initiate a task, then the current task is discarded and the bot switches to the new task according to the event configuration.
    • Any other implicitly paused tasks will also be discarded.
    • Tasks that are kept on hold using Hold and Resume settings are resumed as per Hold and Resume configuration.
    • If the dialog selected to trigger for the sentiment event is not available for any reason, then a standard response is displayed. Refer to the standard response with the title Dialog task required for conversation is not available for more information. (more on standard responses).
  • If the configuration used is to Run the script, then the platform executes the script and continues with the task execution. In case of any errors executing the script associated with the sentiment event, then a standard response is displayed. You may refer to the standard response titled Error in continuing the conversation due to incorrect bot definition for more information. (more on standard responses).
  • In case of a conflict between a sentiment event and direct intent invocation by the user, sentiment event is given precedence.
  • When tone criteria for two or more sentiment events are satisfied at the same instance, then the platform prefers the sentiment event with the highest order of precedence used in defining the events.
Execution Flow for Universal Bots
  • Events configured at the universal bot are honored over the events defined in the child bots.
  • If an event at the universal bot is qualified, then the corresponding behavior is triggered.
  • If an event at the universal bot is not qualified or not defined, then the events defined for the child bot that the user is interacting with are evaluated and triggered if qualified.
  • If no child bot is being executed, then child bot events are not evaluated.

Reset Tone

By default, sentiment values are reset at the beginning of every user conversation session.

Apart from the beginning of the conversation session, the platform resets the sentiment values (i.e. tone scores) once the associated events are triggered. The reset behavior is based on the type of event trigger:

  • If a script is run, then the values are reset after successful execution of the script.
  • In case of a dialog task is triggered, the values are transferred to the new dialog task’s (triggered by the sentiment event) context and reset in the original global context.
Menu