Skip to main content
Loading...
  • Customer Experience
    Customer Experience
  • Employee Experience
    Employee Experience
  • Brand Experience
    Brand Experience
  • Product Experience
    Product Experience
  • Core XM
    Core XM
  • Design XM
    Design XM

Analyzing Text iQ in Stats iQ

What's on This Page:


Was this helpful?


This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

The feedback you submit here is used only to help improve this page.

That’s great! Thank you for your feedback!

Thank you for your feedback!


About Analyzing Text iQ in Stats iQ

Have you ever wanted to see how your open-ended responses correlate with more quantitative data? For example, are customers who address “ease of use” in their feedback also more likely to mention your mobile app? If customers tend to have a higher sentiment when they mention your support team, are they also more likely to give higher NPS ratings for your entire company? To answer these questions and more, Text iQ variables, such as topics and sentiments, can be analyzed with Stats iQ.

Qtip: This feature is also available for Stats iQ in CX Dashboards. Both survey-specific and dashboard-wide Text iQ data can be analyzed in Stats iQ in CX Dashboards.
Qtip: When making changes to Text iQ (such as adding new topics), it may take some time before these updates are available to sync in Stats iQ.

Text iQ Variables Compatible with Stats iQ

Stats iQ is compatible with the following Text iQ variables:

  • Topics: Topics are the subjects mentioned in an open-ended response that you wish to analyze. Topics are a means of categorizing or tagging responses so you know what the respondent addressed in their feedback. When imported into Stats iQ, there will be a Topics variable for each topic created in Text iQ. This variable is a Checkbox variable type.
    Qtip: Reduce survey fatigue: instead of asking about every aspect of your program, let respondents bring up the parts that matter most to them. By analyzing topics brought up by your respondents during feedback, you reduce the number of distinct questions you have to ask respondents.
  • Parent Topics: Parent Topics act as a sort of umbrella over other topics. For example, your restaurant may have separate topics for each dish, and then nest all these topics under a “Menu” parent topic. When imported into Stats iQ, there will be a Parent Topics variable for each parent topic you’ve created. This variable is a Checkbox variable type.
  • Sentiment: This is how Positive, Negative, Neutral, or Mixed a response seems to be. The sentiment is available for each topic that appears in your response, as well as for the response overall. This variable is a Category variable type.
  • Sentiment Score: This is a -10 to +10 score for the sentiment of a comment. For example, a very intense, positive response such as “I love Love LOVE YOUR COMPANY!” would score a +10. An intensely negative response, such as, “I UTTERLY DESPISE your company!” would get a -10. A 0 is a neutral score. This variable is a Number variable type.
  • Sentiment Polarity: This is a 0 to 10 score for the polarity of the comment. This is a calculation of how mixed the comment is. For extremely positive and negative Sentiment Scores (like the previous examples), there’s usually a corresponding 0 polarity. But for a comment such as “I love your food, but your restaurant is so dirty,” you will get a more nuanced score. This variable is a Category variable type, but can act as a Number instead.

image of text iq variables in stats iq
Before you can bring these variables over into Stats iQ, they must exist! Make sure you open Text iQ and analyze your responses.

Analyzing Text iQ Variables

Once you’ve conducted your text analysis and made sure all new responses are loaded in Stats iQ, you can analyze your Text iQ variables just like all your other variables. Whether you choose to describe your text variables, relate them to other variables, perform regressions, or build pivot tables or clusters, text variables are as flexible as any other data point in your workspace.

example of a statistical analysis run on text iq variables

Example Analyses

  • Relate the topic to important output variables.
    Example: People who mention the topic “customer support” tend to have lower overall satisfaction scores. This implies customer support has a pretty big impact on the overall company CSAT, and we should investigate what changes we can make in this area.
  • Relate the topic to details about the respondent or interaction.
    Example: People who mention the topic “enterprise software” tend to be younger and more affluent, as shown by this topic’s high correlation with certain age and income demographic variables.
    Example: People who shopped at the store in Seattle frequently mention “low quality,” but the people who shopped at the Dallas location don’t. This implies the Seattle store has changes to make that the Dallas store doesn’t.
  • Relate a topic to Time. Is the mention of a topic becoming more prevalent over time?
  • Relate a topic to other topics.
    Example: If the topic “wait time” is associated with the topic “drive-through,” you’d probably take a different action to fix the problem then if “wait time” were associated with topic “in-store eating”.