Open-Ended Text Use Case

A guide to implementing Relevance AI open-ended text use case, including data structure and sample questions.

Problem Statement

Understanding verbatim comments, answers to open-ended survey questions, is often key to unlocking insight. Identifying emerging themes from text data often forms part of strategic initiatives required for executive reporting - such as in the context of customer or employee feedback projects/surveys - or ongoing business operations, such as in the context of customer service and support teams, requiring insight to be presented at team standups or weekly huddles.

Who Are the Typical Editors and Viewers of This Use Case?

  • Editors: Market Researchers, Insight Analysts, Business Analysts, Data Analysts
  • Viewers: Insight Managers, Research Managers, Project Managers, Team Leaders, Customer Teams, Chief Experience Officers, Chief Customer Officers

How Does It Work?

An Example of Data Structure: Open-Ended Text Use Case

Right-click and 'open image in new tab' to expand the view.

Right-click and 'open image in new tab' to expand the view.

Please refer to this article for more information about preparing data.

Text Fields

A text field, also called a string variable, is a qualitative open-ended response. Here are some of the typical text fields we find in a survey use case used in Relevance AI:

  • Open-ended customer feedback. Answers to questions like: Please give reasons for this rating
  • Identify opportunities for improvement: The single biggest improvement we could make to the website for you is?
  • Impact analysis: If, at all, how has this impacted you to date?
  • Product feedback: Which features and functionality do you most like to use and why?


A measure is a quantitative, numeric value. Here are some of the typical measures we find in survey data used in Relevance AI:

  • Feedback Metrics: Satisfaction, Net Promoter Score (NPS), Revenue, Sales, Financial Metrics

String or Categorical Fields

Unless a numeric measure, Relevance AI treats all other fields as string variables. Here are some of the typical string fields we find in a survey use case used in Relevance AI:

  • Customer Demographics: Gender, Age, Location, Education, Income etc.
  • Product characteristics: Product category, Product sub-category, Product type, Product name, etc.
  • Team attributes: Team Name, Region, Channels, Sales Office Location, Account Manager, etc.

What Sort Of Insights Can Relevance AI Help Me Uncover?

Identify Key Themes

  • Understand emerging themes driving customer feedback / satisfaction
  • Summarize open-ended responses with both high-level tags and granular sub-tags

Understand Feedback Patterns

  • Filter by customer sentiment: positive, negative, neutral
  • Pinpoint feedback by emotion: e.g. anger, dissapointment, frustration

Uncover New Opportunities

  • Understand satifaction across key customer demographics
  • Satisfaction by channels, products, regions
  • Track themes over time (time series data)

How To Get Started: Open-Ended Text Use Case

Recommended Workflow


  • Experiment with clustering. Finding the optimal number of clusters requires at least a few Clustering and reviewing the results
  • Spend time reviewing the AI suggested tags before actually tagging the dataset. This will decrease the edit time.
  • Include all fields that you might need to extract insight when analysing your data
  • Make sure to anonymize sensitive data before uploading your data. Alternatively, you can use anonymize but a review over the results is highly recommended.

Related Articles

How to prepare data

How to upload data

Quick guide to find and create insights

Tips to improve tagging

Explorer dashboard