How can we help you today?

Galaxy: More than a Concept Cloud

Modified on: Tue, Jul 9, 2019 at 1:33 PM

Traditional word clouds

A word cloud is a two-dimensional visualization of text data, where the size of each word it contains indicates its frequency in the dataset. Words are placed next to each other as it’s generated for aesthetic, rather than functional, effect.

Why Galaxy is different

The Galaxy feature provides much more than a traditional word cloud. It’s comprised of 150 dimensions of associations between concepts. Word cloud frequency can mislead, as there are words which are common in basic expression that don’t actually confer analytic value. Instead, Galaxy prioritizes the concepts that are more prevalent in your data set than would be expected to appear in the underlying language. Each concept is alongside its most closely associated concepts, and seven of the largest clusters of conversation are highlighted in different colors for at-a-glance insight.

Try it: click and drag any concept, and as you move your cursor, the Galaxy spins to help you visualize its 150 dimensions. Letting go of the concept flattens the view as if it were under a pane of glass, so you can perform quadrant analysis in two dimensions.

Galaxy displays the top 500 most important and frequently occurring concepts in your project. Concepts can be single words or short phrases.

Font size

Concepts in a larger font size are the most frequently used in the data set. The largest concepts in the Galaxy dictate the overarching context of a particular discussion. Since they are very common, they are likely concepts you already presume the dataset is about.

Smaller- to medium-size terms are often the most interesting and meaningful terms within a discussion/context, and a good starting point for data investigation and discovery.

Proximity and Colors

If “web site” and “didn’t receive my order” appear in close proximity to one another within your DCC, this indicates that these two concepts are related, which provides more specific context and justifies further investigation by examining additional specific data points in that location within your dataset. Read the verbatims to understand the association between concepts.

When you first launch a project, the system automatically suggests topics and groups them into the 7 most prominent discussion, each containing the top 4 concepts per discussion. These Auto-Topic Suggestions are automatically grouped together and assigned a color. You can then edit these suggestions (keep or dismiss suggestions) to include your own topics and assign your own colors.

Alternatively, you can search for or select a concept. The heat map effect activates in the DCC and instantly highlights related concepts to indicate which other concepts are associated with that term. Your selected term will appear in red, and its most closely related concepts will appear as dark blue, and lesser-related terms in light blue. Concepts in gray have a weak relationship to the selected term or are unrelated all together in a particular data set. 

NOTE: Concept Search will find any term that exists in the data set, whether it is displayed in the DCC or not. Therefore, if you search for a term in the search box and do not see it highlighted inside the DCC, then it is simply not one of the top 500 concepts in this project. When no concepts are selected, the Galaxy also displays colors based on any saved Topics in the project. 

See "How do I save topics that I've search for?" for more information about creating and saving Topics. Colors in this Galaxy correspond to colors assigned as Auto-Topic Suggestions


The axes are set to display the maximum variance between terms.  This causes major related concepts to form clusters which (roughly) represent the most prominent conversations in the data and dictate context for a particular concept within a discussion. You can change the shape of the DCC by clicking and dragging terms, or by setting a topic as either the X or Y axis. Drag a concept to the upper left quadrant (or to any outer edge) and related concepts will follow. This exercise helps isolate discussions so you can visualize major themes around a concept.

You can set topics as Axes, which rearranges the DCC so that concepts most related to the topic selected are grouped closer together on one side of the axis, while concepts least related to the topic selected are grouped together on the other side of the axis. As a default, no topics are set as either axis.

You must have saved Topics in order to proceed.

  • To set the axes, click Auto X-axis and Auto Y-axis (under the Galaxy). A menu will appear with the list of saved Topics.

  • Select a topic for each axis and the Galaxy will reconfigure itself automatically.

  • Look to the upper-right quadrant for the "intersectionality" of your selected topics.

Click the axis overlay icon to superimpose quadrants to enhance the visualization for this data discovery technique.

You can reset the Galaxy to its original position by clicking the circular arrow.

Did you find it helpful? Yes No

Send feedback
Sorry we couldn't be helpful. Help us improve this article with your feedback.