Build and Optimize User Experiences With Bots That Understand Human Emotion

Request a Demo

Trigger conditional flows and steer user-bot conversations with sentiment analysis and tone processing. Bots built with Kore.ai analyze the emotional state of users and callers and model their response to provide excellent service.

  1. Home
  3. Platform
  5. Intelligence
  7. Sentiment Analysis

Why businesses need emotionally-aware chatbots

Although many brands are looking to replace, or at least augment, their traditional call center experience with emerging technologies such as bots, they don’t want to lose that human touch. Sentiment analysis allows bots to ‘understand’ the mood that the user is in by deciphering verbal and sentence structure clues. Bots can handle the happier customers themselves while transferring the unhappier customers to human agents.

Sentiment Analysis

Kore.ai’s NL engine parses user utterances for specific words, phrases, and modifiers, such as connotation and word placement, that typically correspond to different emotional states. Our engine then generates – in real-time – average tone scores that are used to assess user input, trigger custom flows, bring in human agents, and steer conversations.

Sentiment Types

Emotions influence the choices people make, the way they interact with others, and the perception they have of the world around them – including your brand. Our platform analyzes user utterances and classifies them based on detected levels of anger, disgust, fear, sadness, joy, and positivity.

Emotions, however, are not mutually exclusive and are usually experienced along a gradient. Our tone algorithm and platform intelligence accounts for this reality and can uncover and score multiple emotions in a single utterance. For example, an input could yield a high score for joy, but a mild score for sadness at the same time.

Sentiment Scoring

Our NL engine scores and ranks sentiment on a scale of -3 to 3, based on the intensity of the sentiments detected. This number represents how much or how little the user input corresponds to each of the six core emotions.

Kore.ai provides sentiment analysis results as context object variables at two different levels:

Individual Message: Tone emotions and scores are provided for the current user-bot exchange.

Aggregate: Average tone emotions and scores for the entire session.

Conditional Transitions

Sentiment scores can be stored as context and used to drive the flow of a dialog task via conditional transition statements. This allows developers to use these scores to steer user-bot conversations or seamlessly invoke escalation to a live agent.

Improve Your Customer Experience and Increase Conversion Rates With Sentiment Analysis

Flexible Customer Service

Bots can adapt their service to the mood of the customer early in the conversation. Empathetic service makes for great, memorable experiences for customers.

Seamless Routing

Irritated customers can be quickly identified and escalated to the appropriate person or channel, nipping potential issues in the bud.

Generate Upselling Opportunities

Identify your happiest customers with sentiment analysis, as they tend to be more receptive to spending more. Avoid upsetting disgruntled customers with unwelcome sales pitches.

Identify Key Emotional Triggers

Emotional triggers drive human decision making. Our platform collects all sentiment data, helping you discover trends and triggers. This is useful for bot dialog development and for creating effective marketing and sales materials.

Track Overall Satisfaction

Detect changes in the overall opinion of your brand, service, and chatbots. Our platform provides insight into how your customers are feeling whenever they interact with you and your brand.

Featured Resources

Kore.ai Bots Platform
Architecture

Download Datasheet

How to Build an Enterprise-Class Bot Platform

Read Blog

20 Minute Bot Builder
Demo

Watch Video
20 Minute Bot Builder Demo

5 Things That Are Triggering a New Era of Intelligent Chatbots

Read Blog
Menu