Automated Text Analytics

Suite
Customer Experience
Product
Qualtrics
What's on this page

About Automated Text Analytics

Do you have a set of text interactions that you’d like to analyze for common topics and themes? You can jumpstart a topic model by using Artificial Intelligence (AI) to build a topic hierarchy. Using a diverse set of inputs including your unstructured customer data, use case, persona, industry, and additional context information, you can leverage AI to build a topic hierarchy, enabling you to identify the themes most important for your business use case.

Qtip: This page covers creating an automated topic model in Qualtrics. See Topic Hierarchy Generator in XM Discover for information on building an AI-Assisted model in XM Discover.

Qtip: You cannot use AI to build topic models based on any EX projects (Engagement, etc).

Requirements

User Permissions

To build a topic model using AI, you need the Automated Text Analytics user permission enabled for your account. If this permission is disabled, the “Text Analytics” section will not appear in your navigation menu.

Supported Data

You can analyze unstructured data from the following Qualtrics project types:

  • Survey projects
  • Imported data projects
  • Online reputation management project
  • Email data project
  • Chat data project
  • Voice project

Please note that you can only create automated topic models for a project if that project does not already have any Text iQ models associated with it. This includes models created in both the Text iQ tab of a project or the Text iQ section of a dashboard using the data modeler. If you select an ineligible project, you will receive a warning that the project already has Text iQ fields.

receiving an error that the selected project already has a Text iQ model associated with it
receiving an error that the selected project already has a Text iQ model associated with it

Qtip: If you’d like to use a project that already has been analyzed with Text iQ, you must:

Export your topics from Text iQ in that project.

Delete the Text iQ topic model. Please note that manual tags will not be carried over to automated text analytics.

Load the source project in your desired dashboard using the data mapper.

Use Text iQ from the dashboard and upload the previously downloaded model there.

Generating a Topic Model

Select Text Analytics from the global navigation menu.
clicking "generate a new model" in the text analytics tab
clicking "generate a new model" in the text analytics tab
Click Generate a topic model.
Give your model a name so you can identify it later.
giving the model a name and selecting Engage as the data source
giving the model a name and selecting Engage as the data source
Select Engage for the source.
Qtip: See Topic Hierarchy Generator in XM Discover for steps on generating a model using data from XM Discover.
Choose the project(s) you’d like to analyze. You can select up to 10 projects.
selecting the projects and fields to include
selecting the projects and fields to include
Qtip: See the Requirements section above for information about what data is eligible to be selected here.
For each project, select the text field(s) you’d like to include in the analysis.
Click Next.
Choose Let Qualtrics AI build it to use AI to build the hierarchy.
choosing the option to build an AI powered hierarchy
choosing the option to build an AI powered hierarchy
Qtip: The “Upload your topic hierarchy” option is useful if you have an existing topic hierarchy in JSON format that you’d like to reuse instead of generating a new hierarchy.
Click Save.
Enter your organization’s name.
.
.
Select your industry.
Qtip: If your industry isn’t listed here, you can click “Add” and then specify your industry in the text box.
Click Save.
Enter the role in the company of the user persona who will use the topic analysis output (e.g., Employee Experience Manager, In-store Manager).
enter the role for the person using the topic model and enter a use case for the model
enter the role for the person using the topic model and enter a use case for the model
Enter a use case for the hierarchy. There are example use cases available as a starting point.
Click Save.
Choose the number of levels in your hierarchy. You can have between 1 to 5 levels; generally we recommend 3-5 levels for an in-depth analysis.
choosing the number of levels to include in the hierarchy
choosing the number of levels to include in the hierarchy
Click Save.
If desired, you can enter any extra information about your company, industry, products, and services to help further customize the model.
adding extra context for the model and generating the hierarchy
adding extra context for the model and generating the hierarchy
Click Save.
Qtip: If needed, you can click Edit to change any part of the model parameters before generating the text hierarchy. You cannot edit these parameters after your hierarchy is generated.
Click Generate. It will take a few minutes for your model to be ready.
Once the model is ready, click Review.
clicking Review
clicking Review
You can click through the hierarchy and deselect any topics you do not want in your hierarchy. If you deselect a parent topic, all children topics will also be deselected.
reviewing the model and deselecting any unwanted topics
reviewing the model and deselecting any unwanted topics
If desired, you can send feedback to Qualtrics about your generated model to help improve generation in the future.
Click Accept topics to build the hierarchy.
After your topic hierarchy is created, you can manage it from the Text Analytics page. Here, you can edit the topics in your model, modify the connected sources, and share the model with other users in your license.

Qtip: You can repeat these steps while modifying the inputs to generate a new model (for example, to create a model tailored to a certain role at your organization).

Importing a Topic Model

Follow the steps in this section to import a topic model from a JSON file. Typically, this file is exported from an existing Text iQ dataset.

Qtip: This option is only available for Qualtrics Platform data sources.

Select Text Analytics from the global navigation menu.
clicking "generate a topic model" in the text analytics tab
clicking "generate a topic model" in the text analytics tab
Click Generate a topic model.
Give your model a name so you can identify it later.
Select Engage for the source.
giving the model a name and selecting Engage as the data source
giving the model a name and selecting Engage as the data source
Choose the project(s) you’d like to analyze. You can select up to 10 projects.
selecting the projects and fields to include
selecting the projects and fields to include
Qtip: See Requirements for information about what data is eligible to be selected here.
For each project, select the text field(s) you’d like to include in the analysis.
Click Next.
Select Upload your topic hierarchy.
importing a topic hierarchy via JSON file
importing a topic hierarchy via JSON file
Click Choose file and select the JSON file saved on your computer.
Click Save.
Click Upload.
If desired, you can deselect any topics you do not want to include in your new model.
deselecting any unwanted topics and saving
deselecting any unwanted topics and saving
Click Accept topics.

Using an Automated Topic Model

Qtip: Automated Text Analytics comes with support from a Qualtrics representative, such as an Implementation Consultant or a Technical Success Manager. This representative will take care of implementing Text Analytics into a dashboard data setup.

After creating an automated topic model, the generated topics will be tagged to the data source(s) used for the model. You will be able to see these topics in the Data & Analysis tab of your project, much like any other text topic fields.

viewing the ai topic fields in the Data & Analysis tab of the project
viewing the ai topic fields in the Data & Analysis tab of the project

Your automated topic model will also create a “Granular Text Analytics” data source that has the structure of all sentences from source interactions. For each sentence, there will be associated topics, sentiment, effort, emotion, emotional intensity, and actionability fields. This data source is available in the CX dashboard data modeler.

After you have your new source containing text enrichments, you can display it in a CX dashboard. Currently, this is managed by your Qualtrics team. Your new source containing text enrichments will be joined with your original interaction data, and linked dashboard fields are used to link the same field across interaction and derived datasets. Once your dashboard’s data is set up, you can choose which datasets(s) you want to use on an individual widget and filter basis.

Viewing a dashboard that has text topic data displayed in it
Viewing a dashboard that has text topic data displayed in it

Available Enrichments for Automated Text Analytics

After generating a model, your text responses will be automatically tagged with enrichments that indicate various properties about the response (such as effort, sentiment, emotion, and more). Below are all available enrichments and their meanings: 

  • Actionability: This enrichment categorizes statements that call for a response or action. Possible values include:
    • Request: Contains an implicit or explicit request for information or action.
    • Cry for Help: Requests help or assistance.
    • Churn: Indicates a threat of losing clients.
    • Cancellation: Indicates a threat or intention to cancel membership, service, or transactions.
    • Suggestion: Contains an implicit or explicit suggestion for change.
    • Missed Commitment: A promise, product, or service was not delivered.
    • Consequence: An event resulting from something else (e.g., a cancelled delivery).
  • Emotions: This enrichment labels the feeling expressed in respondent feedback.
    • Possible values include: Anger, Boredom, Confusion, Disappointment, Disgust, Doubt, Embarrassment, Fear, Frustration, Helplessness, Sadness, Longing, Surprise, Amusement, Anticipation, Happiness, Love, Pride, Relief, Thankfulness, and Trust.
  • Emotional Intensity: This enrichment indicates the strength of the expressed emotion and is only present when emotion is detected. 
    • Possible values include “High” and “Low.”
  • Sentiment: This enrichment indicates the overall sentiment, from very negative to very positive. The “Very Negative” and “Very Positive” sentiment labels indicate the strongest sentiment, helping you to focus on the most critical feedback in each comment. “Neutral” sentiment does not show strong emotion in either direction. “Mixed” sentiment suggests there is a mixture of positive and negative sentiment in the same statement. Sentiment labels have the following numeric scores:
    • Very Negative recodes to -2
    • Negative recodes to -1
    • Mixed recodes to 0
    • Neutral recodes to 0
    • Positive recodes to 1
    • Very Positive recodes to 2
  • Effort: This enrichment measures the effort it took a person to complete a task and can help you identify products and services that cause pain or delight. Effort labels have the following numeric scores:
    • Very Easy recodes to -2
    • Easy recodes to -1
    • Mixed recodes to 0
    • Neutral recodes to 0
    • Hard recodes to 1
    • Very Hard recodes to 2

Was this helpful?

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!