Understanding the Comments Report: Theme, Sentiment and Text Analytics

In this article:


Survey comments offer color and narrative to your survey analytics. But unstructured data is notoriously difficult to turn into insight. And as your comment count increases, this problem just gets worse.

Theme analysis and sentiment analysis offer powerful tools to help users find the story in survey comments. Quantum Workplace’s proprietary algorithms use natural language processing (NLP) to classify comment themes and sentiment. With the help of machine learning, these algorithms get smarter as administrators modify the automated theme and sentiment classifications.

Text Analytics brings together sentiment and themes to help users detect patterns and insights in their unstructured data.

These analysis capabilities extend to comments submitted in a non-English language. Non-English comments will automatically appear in the feed translated to English, however, the original comment in its original language can still be viewed by clicking Show Original Language on the associated comment card. 

Theme Analysis 

As comments are submitted, our NLP engine classifies comments into one of X universal workplace themes. Check out Quantum Workplace's glossary for a complete list of our 36 themes.

These labels are clearly displayed for each comment in the comments report.


Additionally, the Themes list in the lower right of the comments report displays all themes within your current comments, sorted by Count. For a different view, click Sentiment to see a visualization of the Positive, Negative and Mixed scores. 

Themes list with the Count view:

themes list

Themes list with the Sentiment view: 

themes list_sentiment

Modifying themes

Administrators can override any theme by clicking Edit Themes and entering a theme, an auto-complete feature will display existing themes as you type them out. After editing a comment’s theme(s), you’ll need to refresh your comments report for the updated theme count to be reflected.

Note that manually edited themes will appear in a gray tag, whereas automated themes appear inside a blue tag. When hovering over a theme, the administrator who manually applied the theme will be displayed. 

Check out our glossary for the complete list of our 36 themes.

Sentiment Analysis

Sentiment analysis is enabled for surveys by default. At survey close, our NLP engine classifies comments with one of four sentiment classes:

  • Negative (Red): represents things that employees don’t like, think can be improved, or both.  
  • Positive (Blue): represents things that employees like, think are going well, or both. 
  • Mixed/Neutral (Gray): represents things that employees have either mixed or neutral feelings about. 
  • Unclear (White): represents a comment that can't be confidently identified.

These labels are clearly displayed for each comment in the comments report.

theme dropdown 4

Additionally, the sentiment distribution displays the breakdown of sentiment within your current comments.

themes list_sentiment

Modifying sentiment

Administrators can override this sentiment by clicking the sentiment button and selecting a sentiment from the list. After modifying comment sentiment, you’ll need to refresh your comments report for the updated sentiment distribution reflected. Learn about how Quantum Workplace measures sentiment.

Text Analytics 

Text Analytics brings together comment themes and sentiment to help users find the story in unstructured data.

Most Negative & Most Positive Themes

In the right pane titled Theme Analysis, you can see the three Most Positive and Most Negative themes in the two columns. 

theme analysis 1

Theme Sentiment Bubble Chart 

By clicking More Text Analytics, you can view the prominence and net sentiment of your themes visually via a bubble chart. 

more text analytics 1

bubble chart 1 v2

You can view the chart in full-screen or download the chart in various formats by clicking the icon to open additional options. 

Net Sentiment (X-axis)

The X-axis represents the “net sentiment” of each theme. Net Sentiment is the result of taking % positive - % negative. The more negative a theme’s net sentiment, the further left it will appear on the X axis. The more positive a theme’s net sentiment, the further right it will appear. 

Theme Frequency (Bubble Size)

The size of each bubble represents the frequency this theme appears in the current comments. Bigger bubbles represent themes that appear more often.


Note: for now, the height of the bubbles (the Y-axis) is randomized. If you refresh your page (or refresh the chart by closing and re-opening “Full-Text Analytics” the Y-values will update). Soon, we hope to modify the Y-values to better use the space (by limiting the number of overlapping bubbles.


  • How does Quantum Workplace calculate sentiment?
    Our automated text analytics uses the "bag of words" model to detect sentiment, which essentially means that our tool breaks each comment down into units called n-grams and looks at the sentiment of each n-gram in order to approximate the overall sentiment of the comment.  

    Unfortunately, this methodology can also fail to detect sentiment:  For example, the comment “I have nothing bad to say,"  the word "bad" would be classified as negative, causing the comment to be incorrectly coded as negative until the sentiment is manually changed by an Admin. 
  • How accurate is your automated theme and sentiment analysis?
    We are currently seeing 80% or higher accuracy. Over time, as the algorithm gets feedback from users overriding its classification, it will learn from these signals and accuracy should only get better.
  • Does theme and sentiment analysis honor filters?
    Yes, the sentiment distribution and theme lists respond to filtering by demographic, by question, by theme, or by keyword will adjust your comment count and sentiment distribution. (Please note that the Theme Sentiment bubble chart currently only responds to demographic filters.)
  • Can sentiment analysis be turned off?
    Yes, contact your Customer Success Manager to turn theme and/or sentiment analysis off for any survey.