Skip to main content
All CollectionsCountHow to use Count
3. Understanding the output from Count
3. Understanding the output from Count

A step-by-step guide, including video tutorial, on how to interpret your Counted data in Yabble.

S
Written by Sarah Goodhew
Updated over 7 months ago


Once your Count is complete, you will be able to see the overall sentiment and theme overview for each counted question in your uploaded data. Count can take anywhere from 30 minutes to 2 hours to process, depending on the size of your dataset, so feel free to navigate away from your project and complete other tasks in the meantime.

If you are on the Yabble home page, you can find your Count project by navigating to ‘Projects’ and clicking on your project name.

You can navigate to this by clicking ‘Hey Yabble’ and clicking on the relevant link for each counted question.

Alternatively, Yabble will show a popup when the Count is complete that you can click on.

You will see the key themes that the AI has found in your data, which you can click into to dive into sub-themes, and even look at each comment that supports each theme and sub-theme.

What can theme counts tell me about my unstructured text dataset?

Theme and sub-theme counts allow you to unlock immense value from your text data. They enable you to see the most talked-about subjects within a particular dataset and can tell you instantly where the biggest drivers and inhibitors of your business lie.

What are themes and sub-themes?

Themes are one- to two-word subjects that highlight the main areas of response within your dataset. These are high-level buckets such as management, customer service, online shopping, and shipping.

Sub-themes add layers of rich detail to your themes. For each theme that Count generates from your dataset, you’ll see all the sub-themes that sit underneath it, be they positive, neutral, or negative. For example:

  • Theme: Parking

  • Sub-themes: Spacious parking spots, Good location, Expensive parking, Too busy/not enough availability

Sub-themes are one of the true goldmines of Count and allow you to:

  • Pinpoint the precise areas where you can improve to drive business growth.

  • Understand customers’ pain points and solve their problems.

  • Make data-driven decisions.

What are sentiment and sentiment scores?

Sentiment gives you an indication of how people feel about a particular subject. Yabble has two distinct level of sentiment, an overall sentiment snapshot and a detailed comment level sentiment which layers into themes and sub-themes.

Overall Sentiment

Overall sentiment indicates the sentiment breakdown within your entire dataset at a glance. Overall sentiment is an aggregate score comprised of the sentiment score of each comment, averaged. It’s displayed as a donut chart at the top of your Count project’s Explore page, identifying the percentage contribution of Negatives, Neutrals, and Positives to your Overall Sentiment.

How is overall sentiment and comment sentiment calculated?

The sentiment score for overall sentiment and comment sentiment is based on a scale of -100 to 100 and is calculated using Google algorithms. The thresholds are:

  • Positive = 15 < x ≤ 100

  • Neutral = -15 ≤ x ≤ 15

  • Negative = -100 ≤ x < -15

This gives you an immediate numerical snapshot of the positive, negative, and neutral feelings around a particular subject. You can view sentiment on an individual comment level, indicating at a glance whether a particular comment is positive, neutral, or negative.

Theme and Sub-Theme Sentiment

Yabble calculates sentiment for each individual theme and sub-theme, displaying sub-theme sentiment in the form of an emoticon. Positive is green, neutral is orange, and negative is red. (For instance: you would see a red emoticon next to the Parking > Small spaces sub-theme.) If you hover over the emoticon, you’ll see a detailed count and percentage breakdown of the positive, neutral, and negative buckets.

You can view sentiment on an individual comment level, indicating at a glance whether a particular comment is positive, neutral, or negative. This is a more detailed level sentiment. Every theme and sub-theme generated from a comment is given a sentiment.

For example

Comment: My shop today was ok. I enjoyed the range of seasonal produce but did have to use self-checkouts as no cashiers were available which I don’t like to do.

  • Theme: Overall Satisfaction

  • Sub-Theme: Shopping experience was ok

  • Sentiment: Neutral

  • Theme: Range

  • Sub-Theme: Good range of seasonal produce

  • Sentiment: Positive

  • Theme: Checkout

  • Sub-Theme: No cashier service available

  • Sentiment: Negative

This comment has generated three themes and sub themes, each with their own sentiment. Sentiment is displayed in the form of an emoticon. Positive is green, neutral is orange, and negative is red. (For instance: you would see a red emoticon next to the Checkout > No cashier service available sub-theme). If you hover over the emoticon, you’ll see a detailed count and percentage breakdown of the positive, neutral, and negative buckets.


How does the filter functionality work?

The filter functionality allows you to filter by different variables and to focus on certain segments of your results. You can filter by:

  • Anything you upload (these data parameters come through as custom variables, including demographics, custom questions etc.)

  • Response date

  • Comment sentiment

  • Themes

  • Theme sentiment

Future releases will include the ability to filter by sub-themes as well.

What can I see on my Count project Explore page?

Your Explore page displays a clear, concise visualization of the analysis Count has performed on your dataset.

Your overall sentiment score sits at the top, next to a box linking you to Gen, enabling you to run a start a chat with your data straight from your counting results.

Below your sentiment score, you’ll see your ‘Theme overview’ with a table of the themes and nested sub-themes. You’ll also see the Comments/Filters sidebar to the right.

Themes are displayed at the top-level from your dataset, alongside percentage and sentiment scores for each. Percentage indicates the frequency with which that theme arose during analysis.

If you click the arrow (>) next to a theme, your sub-themes will populate underneath, alongside their own percentage counts and sentiment (displayed as emoticons).

If you select ‘Sub-themes’ from the drop down, you will see all your sub-themes in one list. They’re ordered from highest to lowest count, irrespective of their parent themes — but you can see the corresponding theme listed next to each in parentheses (i.e. Spacious parking spots (Parking)). Note: the order of sub-themes in the overall Sub-themes tab may differ from the order of sub-themes under each parent theme.

Hovering over the emoticon next to a sub-theme will generate that sub-theme’s individual sentiment score (counts and percentages for positive, neutral, and negative).


Now that you have interpreted your Count results, you can check out some of the more advanced ways to use Yabble Count in our 'Getting the most out of your Count insights' module.

Did this answer your question?