By default, the Analysis page displays results as Comments. The buttons to switch between the different results pages are displayed in the upper right corner.
Ordered from left to right, these buttons will take you to the different ways of displaying your results: Comments (default), Topics or Opinions. Each one offers a unique perspective of the results.
These three ways of displaying results can also be applied to Blacklists.
If you need a quick refresher on the difference between these concepts, revisit the article How does Keatext analyze comments?.
The Comments display shows results in the natural language format, ranked by record frequency. This display helps you understand the context quickly and easily. It is the default display.
Of the three displays, this one offers the highest level of detail into what was expressed by the commenter. Each row represents a Comment, which is a combination of one Topic (and all synonym variations), one Opinion (and all synonym variations) and the assigned sentiment category.
When selecting a Comment checkbox, the user has the option of hiding the Comment (sending to a Blacklist).
When you click on a Comment you are presented with additional analytics: the number of Total Commenters, the Sentiment Score, the Level of Interest, Correlations and Records. The Topic group and the Opinion group that the comment belongs to and access all related Records are shown at the bottom of the display.
The Topics display helps monitor what is top of mind for commenters. This helps prioritize what business areas are most relevant. It shows the Topics in order of frequency, the distribution across the different sentiment categories, and a count of the number of times it is present in the comments.
Let's look at an example. In the screenshot below, the most frequent Topic is "Location". This is what is top of mind for customers in the reviews we analyzed. It showed up mostly as Praises, with a comparatively small amount of Problems and Mentions, and some Suggestions.
When you click on a Topic you are shown a similar display as on the Comments page with one difference -- the Level of Interest chart is broken down by sentiment.
When selecting a row in the Topic display an additional functionality called Merge will appear. This will merge the selected Topics into one group. In the screenshot below, we have selected "Food" and "Restaurant" to be merged since, in the context of this dataset, they express the same concept. Read more on customizing groups here.
The default way of displaying results is as a list. However, the user can choose to switch the Topics display to a chart. The chart is a stacked bar that displays the proportion of sentiments expressed regarding each Topic. Hover your mouse above the chart to get a full breakdown. You can easily export the Topics chart and add it to your presentation.
The Opinions display shows at a glance how commenters qualified the service or products they have given feedback on. This is a good display for brand management or users wishing to explore customer or employee emotions. The Opinions display ranks detected Opinions in order of comment frequency.
The Opinions display has the same features as the Topics display (Merge, Chart and Volume Trend etc).