Comments, Topics and Opinions can be broken down by Metadata fields to reveal Volume and Sentiment trends.
Anywhere you can drill down to records on the dashboard (Bar Charts and Heatmaps) you can create Metadata Correlations.
Metadata Correlations can be used, for example, to find out if different categories of customers value different things using location or demographic metadata: Male vs. female, different age groups, level of education, and place.
In the example below we are looking at online reviews of the Uber Eats app.
The Comment Details popup has tabs displaying Records, Correlations and the Level of Interest over time. Select the Correlation tab to reveal a bar graph that can be adjusted to whichever metadata field you choose. In this case we have broken down the data for the city of Chicago further to see the relative distribution of sentiment between male and female genders. Males from Chicago have more negative sentiment towards Uber Eats than females, perhaps a marketing effort could be aimed in that direction.
The metadata field can be adjusted by choosing from the dropdown accessible by clicking the filter icon at the top-right of the graph. You can show up to 12 bars. Use the toggle to break down further by sentiment and display as absolute volume or relative distribution.
The same can be done with Heatmaps. Heatmaps show the intersection between two variables, in the case a Topic and an Opinion. The paring of Customer Service and Worst have been broken down by age.
The two age groups that need the most focus are the 25-39 years old as well at 65+ years old.