All Collections
Data
How to create Custom Themes?
How to create Custom Themes?
Learn more about Custom Themes and add your expertise on top of our AI-generated topics to create reportable insights.
Trish Pencarska avatar
Written by Trish Pencarska
Updated over a week ago

In this article:

What are Custom Themes?

Custom Themes gives you the power to create your own categories, so you can better understand the specific needs of your customers. By selecting topics aligned with your industry's language, you eliminate complex workarounds and improve topic identification accuracy.

In addition, Custom Themes enables you to measure relative difference between specific topic groups. This helps you extract valuable insights and make more informed decisions.

How to define Custom Themes?

Before you start defining your Custom Themes, you will need to create a comparison using Explore.

  1. Start exploring your results and determine what kind of topics you want to group together in your data. You may also identify words that are categorized in a way that doesn't make sense for your industry.

  2. Click on the blue box with a flag icon on the right-hand side to launch the side panel.

  3. Select 'Create theme' and give it a name, then click 'Create.'

  4. Drag and drop the relevant topics to create your bespoke group of themes.

  5. You can also create sub-themes by grouping individual words together using drag and drop. If you have used Heartbeat before, you may already be familiar with this feature.

  6. Once your Custom Themes are ready, you can filter your topics.

  7. Save your Custom Themes. They will be accessible from the library and can be applied to any project.

Exporting data associated with Custom Themes

You can export the associated data if you want to feed your Custom Themes into an external reporting dashboard.

1. Locate your desired Custom Themes, by filtering via custom topics.

2. Click the 'Export options' icon from the top menu and select CSV.

3. The data export will provide you with message frequency in both data sets, relative message frequency in both data sets, and relative difference.

Common use cases for Custom Themes

Get more accurate results for your specialized vocabulary without workarounds

Most people would associate seats with furniture and that’s how they would appear on our list of pre-defined topics. However, seats are a part of the rolling stock for a train operator, so the Insight Analysts working within the rail industry can now categorize them accordingly.

Set your own groupings in order to get the measurable metrics from your text data

An organization used to manually tag and analyze customer feedback comments, which was time-consuming and prone to errors.

With Custom Themes, based on their own set of categories, they can now quickly see the frequency of certain comments and split data based on positive vs. negative drivers. This has allowed them to provide more accurate and timely reports and identify areas for improvement.

Did this answer your question?