Which attributes can I compare?

deepsight suggests columns with categorical values from your data, such as region, age group or channel. You choose which ones to use. To compare channels or platforms, upload the data in one file with a column for the channel.

Can I set the minimum base myself?

No. The thresholds are fixed: values below a base of 10 responses are flagged or hidden, and significance indicators start at 30. They are a statistical indicator, not a protection for small groups: quotes and exports remain readable.

Does this work with NPS data and rating scales?

Yes. You compare NPS and sentiment between groups and cross rating scales with attributes; for scales, deepsight shows the mean as well as top-2 and bottom-2 shares. You decide which end of the scale counts as good.

Can I add group comparisons to a report?

Yes. You add group comparisons and cross-tabulations to a report and export it to PowerPoint; you export data with result columns to Excel or CSV.

deepsight cloud · Group comparison Compare groups.

Which topics and ratings differ between your customer groups? Choose suitable attributes from your data – deepsight suggests columns that fit.

Example

Topics by attribute

Choose an attribute from your data.

Topic	New customersn = 318	Existing customersn = 886
Delivery time	29% (highest value)	21%
Price	18%	26% (highest value)
App	12%	19% (highest value)

Topic	Northn = 402	Centraln = 451	Southn = 351
Delivery time	18%	22%	33% (highest value)
Price	24% (highest value)	23%	22%
App	17%	16%	18% (highest value)

Illustrative values. Share of analyzed responses in a group that mention the topic; multiple mentions possible. Highest value in each row highlighted.

Interpretation

Compare groups. Put differences in context.

A difference between groups shows you where to look more closely – not why it occurs.

AvailableSignificance indicatorsIf you wish, deepsight flags whether a group differs noticeably from the rest of the sample in statistical terms. Indicators start at a base of 30 responses.

AvailableSmall base sizesBelow a fixed base of 10 responses, values are flagged or hidden in group comparison and dashboard views.

AvailableWeightingIn the Explorer, weight your data with a weight column from your dataset or to target distributions (rim weighting). Weights do not automatically make a sample representative.

FAQ

Questions about group comparison

You compare customer groups when analyzing a customer survey, for example – scores and open-ended reasons together.

More features · Analyze responses

Topic analysisOrganize open-ended responses by topic, with new categories or your own codebook.View Sentiment analysisSee for each topic whether a response praises, criticizes or stays neutral.View Intent analysisSort comments by what people want, such as a complaint, praise, a question or an intention to cancel.View NPS analysisCompare topics between promoters, passives and detractors.View

See the feature with your own data

We will walk you through the analysis using an example from your field.

Request a demo