Overview

The Train Verbatim section allows users to review, categorize, and train AI models using actual customer feedback responses (verbatims). It enables you to assign tags, adjust sentiment, and refine text analysis results, ensuring that the system accurately understands customer feedback themes.

By manually reviewing and tagging responses, you improve tagging accuracy, sentiment detection, and topic classification, leading to more reliable insights over time.

When to use it:
Use this feature when you want to validate AI-generated insights, organize feedback into structured themes, and continuously improve analysis accuracy.

Regularly reviewing and training verbatims helps the AI adapt faster to your business context.

Key Use Cases

• Review raw customer feedback to understand context behind responses
• Train AI by correcting sentiment and assigning accurate tags
• Organize feedback into structured themes for analysis
• Identify recurring issues and trends across responses
• Improve accuracy of automated tag and sentiment analysis

How to Use Train Verbatim

How to Access Train Verbatim

1. Go to Text Analysis / Verbatim Section
2. Click Train Verbatim

View Verbatim Responses

The verbatim responses section displays individual customer feedback exactly as submitted. Each response includes respondent name, feedback text, response date, detected sentiment, and assigned tags.

You can browse through responses to review feedback in detail and understand the full context behind customer opinions. This helps validate automated insights with real data.

Reviewing complete responses helps uncover nuances that automated analysis might miss.

Adjust Sentiment (Manual Sentiment Training)

Each response is assigned a sentiment classification (Positive, Neutral, or Negative), which can be manually adjusted based on the actual tone of the feedback.

Updating sentiment directly improves the system’s ability to classify future responses more accurately.

Consistent corrections significantly enhance sentiment detection over time.

Tag Verbatim Responses

Tags allow you to categorize feedback into meaningful themes such as Delivery Experience, Device Quality, Customer Support, or Pricing Transparency.

You can assign, remove, or update one or multiple tags for each response, helping organize feedback into structured insights and improving trend tracking.

Use consistent naming conventions to maintain clean and scalable tagging.

Manage Tags

The Manage Tags panel displays all available tags along with the number of responses associated with each. You can search for tags, view their usage, and select them to perform actions like editing or organizing.

This helps maintain a well-structured and efficient tagging system.

Add Tags

Tags can be created or imported to expand your tagging system and align it with business needs.

Available Methods:

• Generate AI Tags – Automatically creates tags based on patterns in responses
• Add Tags Manually – Create custom tags (e.g., Refund Delay, Product Authenticity, Packaging Quality)
• Import from Survey – Sync tags with survey questions or responses
• Import from CSV – Bulk upload tags for large datasets

Adding tags enables scalable and structured feedback categorization.

Review AI-generated or imported tags to avoid duplication or inconsistent tagging.

Advanced Tag Management Options

When a tag is selected, additional actions become available, including generating subtags with AI, creating subtags manually, grouping tags, converting tags into subtags, editing, and deleting them.

These capabilities help build structured tag hierarchies and enable deeper analysis.

Deleting a tag may impact previously tagged responses.

Tag and Train Verbatim Panel

This panel displays responses along with their sentiment and applied tags, allowing you to directly assign or remove tags and adjust sentiment.

These actions actively train the AI model, improving its understanding of feedback context and sentiment patterns.

Search Verbatim

The search functionality allows you to quickly locate specific responses using keywords.

This is useful for investigating issues, reviewing feedback related to specific topics, and validating tagging decisions.

Run Analysis

Run Analysis applies automated text analysis to verbatim responses, helping extract meaningful insights.

Available Options:

• AI Tag Analysis – Automatically assigns tags
• AI Sentiment Analysis – Classifies sentiment
• Keyword Analysis – Identifies recurring phrases and themes

This helps detect patterns, uncover trends, and surface hidden insights in feedback.

Run analysis after initial tagging to improve the accuracy of automated results.

Apply Filters

Filtering allows you to narrow down responses based on survey questions, tags, or sentiment.

This makes it easier to focus on specific areas of feedback and perform more targeted analysis.

Combining filters (e.g., tag + sentiment) helps uncover precise insights faster.