はじめに
対話型AIプラットフォーム
チャットボットの概要
自然言語処理(NLP)
ボットの概念と用語
クイックスタートガイド
プラットフォームへのアクセス
ボットビルダーの操作
リリースノート
最新バージョン(英語)
以前のバージョン(英語)
廃止機能(英語)
コンセプト
設計
ストーリーボード
ダイアログタスク
ダイアログタスクとは
ダイアログビルダー
ノードタイプ
インテントノード
ダイアログノード
エンティティノード
フォームノード
確認ノード
ロジックノード
ボットアクションノード
サービスノード
Webhookノード
スクリプトノード
グループノード
エージェント転送ノード
ユーザープロンプト
音声通話プロパティ
イベント ハンドラー
ナレッジグラフ
ナレッジグラフの抽出
ナレッジグラフの構築
ボットにナレッジグラフを追加
グラフの作成
ナレッジグラフの構築
既存のソースからFAQを構築
通知タスク
スモールトーク
デジタルスキル
デジタルフォーム
デジタルビュー
デジタルビューとは
パネル
ウィジェット
トレーニング
トレーニングとは
機械学習
機械学習とは
モデル検証
ファンダメンタルミーニング
ナレッジグラフ
示唆
ランキングおよび解決
NLPの詳細設定
NLPのガイドライン
インテリジェンス
インテリジェンスとは
コンテキスト
コンテキストインテント
割り込み
複数インテントの検出
エンティティの変更
デフォルトの会話
センチメント管理
トーン分析
テストとデバッグ
ボットと会話
発話テスト
バッチテスト
会話テスト
デプロイ
チャネル
公開
分析
ボットの分析
NLPメトリクス
会話フロー
Usage Metrics
封じ込め測定
カスタムダッシュボード
カスタムダッシュボードとは
メタタグ
カスタムダッシュボードとウィジェット
LLM and Generative AI
Introduction
LLM Integration
Kore.ai XO GPT Module
Prompts & Requests Library
Co-Pilot Features
Dynamic Conversations Features
ユニバーサルボット
ユニバーサルボットとは
ユニバーサルボットの定義
ユニバーサルボットの作成
ユニバーサルボットのトレーニング
ユニバーサルボットのカスタマイズ
他言語の有効化
ストア
プラントと使用
Overview
Usage Plans
Support Plans
Invoices
管理
ボット認証
複数言語対応ボット
個人を特定できる情報の編集
ボット変数の使用
IVRのシステム連携
一般設定
ボット管理
ハウツー
会話スキルの設計
バンキングボットを作成
バンキングボット – 資金の振り替え
バンキングボット – 残高を更新
ナレッジグラフを構築
スマートアラートの予約方法
Integrations
Actions
Actions Overview
Asana
Configure
Templates
Azure OpenAI
Configure
Templates
BambooHR
Configure
Templates
Bitly
Configure
Templates
Confluence
Configure
Templates
DHL
Configure
Templates
Freshdesk
Configure
Templates
Freshservice
Configure
Templates
Google Maps
Configure
Templates
Here
Configure
Templates
HubSpot
Configure
Templates
JIRA
Configure
Templates
Microsoft Graph
Configure
Templates
Open AI
Configure
Templates
Salesforce
Configure
Templates
ServiceNow
Configure
Templates
Stripe
Configure
Templates
Shopify
Configure
Templates
Twilio
Configure
Templates
Zendesk
Configure
Templates
Agents
Agent Transfer Overview
Custom (BotKit)
Drift
Genesys
Intercom
NiceInContact
NiceInContact(User Hub)
Salesforce
ServiceNow
Configure Tokyo and Lower versions
Configure Utah and Higher versions
Unblu
External NLU Adapters
Overview
Dialogflow Engine
Test and Debug
デジタルスキルの設計
デジタルフォームの設定方法
デジタルビューの設定方法
データテーブルのデータの追加方法
データテーブルのデータの更新方法
Add Data from Digital Forms
ボットのトレーニング
示唆の使用方法
インテントとエンティティのパターンの使用方法
コンテキスト切り替えの管理方法
ボットのデプロイ
エージェント転送の設定方法
ボット関数の使用方法
コンテンツ変数の使用方法
グローバル変数の使用方法
ボットの分析
カスタムダッシュボードの作成方法
カスタムタグを使ってフィルタリング
Data
Overview
Data Table
Table Views
App Definitions
Data as Service
Build a Travel Planning Assistant
Travel Assistant Overview
Create a Travel Virtual Assistant
Design Conversation Skills
Create an ‘Update Booking’ Task
Create a Change Flight Task
Build a Knowledge Graph
Schedule a Smart Alert
Design Digital Skills
Configure Digital Forms
Configure Digital Views
Train the Assistant
Use Traits
Use Patterns
Manage Context Switching
Deploy the Assistant
Use Bot Functions
Use Content Variables
Use Global Variables
Use Web SDK
Build a Banking Assistant
Migrate External Bots
Google Dialogflow Bot
APIs & SDKs
API Reference
API Introduction
Rate Limits
API List
koreUtil Libraries
SDK Reference
SDK Introduction
Web SDK
How the Web SDK Works
SDK Security
SDK Registration
Web Socket Connect and RTM
Tutorials
Widget SDK Tutorial
Web SDK Tutorial
BotKit SDK
BotKit SDK Deployment Guide
Installing the BotKit SDK
Using the BotKit SDK
SDK Events
SDK Functions
Tutorials
BotKit - Blue Prism
BotKit - Flight Search Sample VA
BotKit - Agent Transfer
  1. ホーム
  2. Docs
  3. Virtual Assistants
  4. Analyzing Your Bot
  5. Feedback Analytics

Feedback Analytics

Once you’ve created a Feedback Survey for your conversations based on a survey type (NPS, CSAT, or Like/Dislike), it’s important to constantly monitor and analyze the customer responses, feedback survey scores, and trends over a given period.

Thus, knowing the survey type scores and the key metrics for respondents, responses, trends, and users helps gain actionable insights into the customer experience your business is delivering. The new Feedback Analytics Dashboard under the Analyze section provides prebuilt dashboards to view the survey results and insights based on the duration, survey name, and type you select.

The Dashboard displays graphs and charts derived from real-time feedback data for the following:

  • Distribution trends of feedback scores.
  • The overall score for the given period and its trend.
  • The comprehensive feedback results with an option to export the results for review.

Note: The Feedback Dashboard is available in Release 10.0.0 (January 2023).

Navigating to the Feedback Dashboard

There are two ways to access the Feedback (Analytics) Dashboard:

  1. On the Bot Builder home page, click on your Virtual Assistant.
  2. Navigate to Analyze > Feedback Dashboard

Dashboard Filters

The Feedback Dashboard displays analytics data on the Feedback Survey responses from customers based on the following filters:

  1. Date: Indicates the date range to filter the conversation sessions and capture the survey feedback responses.

Note: The session start time filters the sessions based on when they were initiated.

The filter options include the following:

  • 24 Hours: Captures feedback survey responses from conversations in the past 24 hours.
  • Last 7 Days: Captures feedback survey responses from conversations that happened in the last seven days.
  • Last Month: Captures feedback survey responses from conversations in the last month.
  • Last 3 Months Captures feedback survey responses from conversations in the last three months.
  • Custom: Select the start and end date range on the calendar widget to capture the feedback survey data.

  1. Survey Type: The type of survey including CSAT, NPS, or Like/Dislike. Learn more.
  2. Survey Name: This is the feedback survey name provided when creating a feedback survey under Build > Configurations > Feedback Survey. You can either select All Surveys to capture the Feedback Survey analytics data of all the surveys configured for the virtual assistant or a specific survey name from the dropdown list.

Dashboard Sections

The Feedback Survey Dashboard is categorized into five sections that display analytics-driven graphs and charts for the selected feedback survey name, survey type, and date based on the captured feedback survey responses. These include:

Percentage and Number of Respondents

This widget displays the percentage and the number of respondents for a specific feedback survey response. In addition, it displays the percentage of increase or decrease in the individual response type over the given period.

For the NPS survey type, it captures the data for the following responders:

  • Promoters: Respondents who gave a score of 9 or above.
  • Passives: Respondents who gave a score between 6 and 8.
  • Detractors: Respondents who gave a score between 0 and 5.

For the CSAT survey type, it captures the data for the following responses:

  • Very Satisfied: Respondents who gave a score of 5.
  • Satisfied: Respondents who gave a score of 4.
  • Neutral: Respondents who gave a score of 3.
  • Unsatisfied: Respondents who gave a score of 2.
  • Very Unsatisfied: Respondents who gave a score of 1.

For the Like/Dislike survey type, it captures the data for the following responses:

  • Extremely Likely: Respondents who gave a score of 1.
  • Extremely Unlikely: Respondents who gave a score of 0.

Score Break up – Respondent-wise Survey Score over Time

This section displays the bar chart widget representing the percentage of each response type for Like/Dislike and CSAT surveys and the respondent type for NPS surveys over a time period.

Note: Hover your mouse over the Survey Score chart to see the number of respondents, the response type scores, and the percentage of respondents for each response type at the granular level.

For the NPS survey type, the number of promoters, passives, and detractors is displayed in different colors over the selected period on the days they responded.


For the CSAT survey type, the number of very satisfied, satisfied, neutral, unsatisfied, and very unsatisfied responses received over the selected date range is displayed in different colors.

For the Like/Dislike survey type, the number of extremely likely and extremely unlikely responses captured over the selected date range is displayed in different colors

Survey Score

This section displays the meter graph (from 0 to 100) widget for the survey score based on the actual customer feedback survey responses for a specific survey type. Each score graph is generated based on an internal formula mapped to a survey type as follows:

  • NPS Score: Displays a whole number between -100 and 100 based on the formula (Percentage of Promoters - Percentage of Detractors).
  • CSAT: Displays the percentage value based on the formula (Number of very satisfied/satisfied Respondents / Total Number of Respondents) * 100.
  • Like/Dislike: Displays the percentage value based on the formula (Number of extremely likely Respondents / Total Number of Respondents) * 100.

Survey Trendline

This section displays the widget with the line graph capturing the date-wise response score trend for the total number of positive respondents over the selected date range.

Note: Hover your mouse over the trend chart to see the number of respondents and the response scores on a specific date at the granular level.

For the NPS survey type, the line graph displays the Promoters score trend changes for the total number of promoters over the selected period.

For the CSAT survey type, the line graph displays the Respondents Score trend changes for the total number of very satisfied and satisfied respondents over the selected period.

For the Like/Dislike survey type, the line graph displays the respondents’ score trend changes for the total number of extremely likely respondents over the selected period.

User-level Feedback

This information grid represents the metadata for the Total number of conversations for every unique conversation path between the virtual assistant and the user. This grid summarizes and lists the data of all the feedback surveys mapped to the selected survey type filter. The fields for which data is displayed are:

Field Name Description
Survey Name The name of the feedback survey for the selected survey type.
Kore User ID The internal ID of the user who responded to the survey.
Channel ID The channel ID of the conversation session channel.
Session ID The identifier of the conversation session.
Channel The conversation channel of the user and virtual assistant interaction. This can be a web/mobile client or a messaging platform.
Language The language used to communicate during the conversation session.
Score The feedback survey score.
Date & Time The date and time of the interaction.
Descriptive Feedback

The user’s response to the follow-up question was triggered during the feedback survey.

Note: This value appears only if a follow-up question is configured for a survey.

Note: The values for Score and Survey Name will change based on the selected Survey Type.

Download the Feedback Analytics Report

To download the User-level feedback report, click the Export to CSV icon as shown below:

Feedback Analytics

Once you’ve created a Feedback Survey for your conversations based on a survey type (NPS, CSAT, or Like/Dislike), it’s important to constantly monitor and analyze the customer responses, feedback survey scores, and trends over a given period.

Thus, knowing the survey type scores and the key metrics for respondents, responses, trends, and users helps gain actionable insights into the customer experience your business is delivering. The new Feedback Analytics Dashboard under the Analyze section provides prebuilt dashboards to view the survey results and insights based on the duration, survey name, and type you select.

The Dashboard displays graphs and charts derived from real-time feedback data for the following:

  • Distribution trends of feedback scores.
  • The overall score for the given period and its trend.
  • The comprehensive feedback results with an option to export the results for review.

Note: The Feedback Dashboard is available in Release 10.0.0 (January 2023).

Navigating to the Feedback Dashboard

There are two ways to access the Feedback (Analytics) Dashboard:

  1. On the Bot Builder home page, click on your Virtual Assistant.
  2. Navigate to Analyze > Feedback Dashboard

Dashboard Filters

The Feedback Dashboard displays analytics data on the Feedback Survey responses from customers based on the following filters:

  1. Date: Indicates the date range to filter the conversation sessions and capture the survey feedback responses.

Note: The session start time filters the sessions based on when they were initiated.

The filter options include the following:

  • 24 Hours: Captures feedback survey responses from conversations in the past 24 hours.
  • Last 7 Days: Captures feedback survey responses from conversations that happened in the last seven days.
  • Last Month: Captures feedback survey responses from conversations in the last month.
  • Last 3 Months Captures feedback survey responses from conversations in the last three months.
  • Custom: Select the start and end date range on the calendar widget to capture the feedback survey data.

  1. Survey Type: The type of survey including CSAT, NPS, or Like/Dislike. Learn more.
  2. Survey Name: This is the feedback survey name provided when creating a feedback survey under Build > Configurations > Feedback Survey. You can either select All Surveys to capture the Feedback Survey analytics data of all the surveys configured for the virtual assistant or a specific survey name from the dropdown list.

Dashboard Sections

The Feedback Survey Dashboard is categorized into five sections that display analytics-driven graphs and charts for the selected feedback survey name, survey type, and date based on the captured feedback survey responses. These include:

Percentage and Number of Respondents

This widget displays the percentage and the number of respondents for a specific feedback survey response. In addition, it displays the percentage of increase or decrease in the individual response type over the given period.

For the NPS survey type, it captures the data for the following responders:

  • Promoters: Respondents who gave a score of 9 or above.
  • Passives: Respondents who gave a score between 6 and 8.
  • Detractors: Respondents who gave a score between 0 and 5.

For the CSAT survey type, it captures the data for the following responses:

  • Very Satisfied: Respondents who gave a score of 5.
  • Satisfied: Respondents who gave a score of 4.
  • Neutral: Respondents who gave a score of 3.
  • Unsatisfied: Respondents who gave a score of 2.
  • Very Unsatisfied: Respondents who gave a score of 1.

For the Like/Dislike survey type, it captures the data for the following responses:

  • Extremely Likely: Respondents who gave a score of 1.
  • Extremely Unlikely: Respondents who gave a score of 0.

Score Break up – Respondent-wise Survey Score over Time

This section displays the bar chart widget representing the percentage of each response type for Like/Dislike and CSAT surveys and the respondent type for NPS surveys over a time period.

Note: Hover your mouse over the Survey Score chart to see the number of respondents, the response type scores, and the percentage of respondents for each response type at the granular level.

For the NPS survey type, the number of promoters, passives, and detractors is displayed in different colors over the selected period on the days they responded.


For the CSAT survey type, the number of very satisfied, satisfied, neutral, unsatisfied, and very unsatisfied responses received over the selected date range is displayed in different colors.

For the Like/Dislike survey type, the number of extremely likely and extremely unlikely responses captured over the selected date range is displayed in different colors

Survey Score

This section displays the meter graph (from 0 to 100) widget for the survey score based on the actual customer feedback survey responses for a specific survey type. Each score graph is generated based on an internal formula mapped to a survey type as follows:

  • NPS Score: Displays a whole number between -100 and 100 based on the formula (Percentage of Promoters - Percentage of Detractors).
  • CSAT: Displays the percentage value based on the formula (Number of very satisfied/satisfied Respondents / Total Number of Respondents) * 100.
  • Like/Dislike: Displays the percentage value based on the formula (Number of extremely likely Respondents / Total Number of Respondents) * 100.

Survey Trendline

This section displays the widget with the line graph capturing the date-wise response score trend for the total number of positive respondents over the selected date range.

Note: Hover your mouse over the trend chart to see the number of respondents and the response scores on a specific date at the granular level.

For the NPS survey type, the line graph displays the Promoters score trend changes for the total number of promoters over the selected period.

For the CSAT survey type, the line graph displays the Respondents Score trend changes for the total number of very satisfied and satisfied respondents over the selected period.

For the Like/Dislike survey type, the line graph displays the respondents’ score trend changes for the total number of extremely likely respondents over the selected period.

User-level Feedback

This information grid represents the metadata for the Total number of conversations for every unique conversation path between the virtual assistant and the user. This grid summarizes and lists the data of all the feedback surveys mapped to the selected survey type filter. The fields for which data is displayed are:

Field Name Description
Survey Name The name of the feedback survey for the selected survey type.
Kore User ID The internal ID of the user who responded to the survey.
Channel ID The channel ID of the conversation session channel.
Session ID The identifier of the conversation session.
Channel The conversation channel of the user and virtual assistant interaction. This can be a web/mobile client or a messaging platform.
Language The language used to communicate during the conversation session.
Score The feedback survey score.
Date & Time The date and time of the interaction.
Descriptive Feedback

The user’s response to the follow-up question was triggered during the feedback survey.

Note: This value appears only if a follow-up question is configured for a survey.

Note: The values for Score and Survey Name will change based on the selected Survey Type.

Download the Feedback Analytics Report

To download the User-level feedback report, click the Export to CSV icon as shown below:

メニュー