UPCOMING WEBINAR: Run Research Your Way With AI Skills Displayr AI leverages the elegance and power of Large Language Models to make analyzing text data quick and easy. This article gets you up and running using our Text Categorization module to classify your text data into themes for further analysis, also known as coding open-ends and categorizing verbatims. This is the first step to gaining insight into what your open-ended responses are actually about. For an overview of other text analyses available, please see this article.
- Enable Displayr AI
- Connect Your Data
- Discover and Create Themes with AI
- Classify Responses with AI
- Save Your Classifications
- Report on Your Classifications
Enable Display AI
To enable Displayr AI, click your initials icon (top-right corner) and select Account Settings. Scroll down to the Display AI section of the General tab and update the dropdown to Enabled. A dialog will appear with a link to the terms and conditions, allowing you to accept or decline them. If you decline, then you can still conduct text classification. However, it will use a proprietary machine-learning algorithm rather than an LLM (Large Language Model). For more details, please refer to Displayr AI.
Connect Your Data
Before you can do any analysis, you'll need to get your data into Displayr. Displayr can handle file uploads from your computer (e.g., Excel, CSV, or SPSS files), from a URL, SQL database connections, R code, or using pre-built API integrations (e.g., Qualtrics, Forsta). The full list of supported data sources is found in How to Import Data into Displayr.
To connect your data, click Data Sources > Plus (+). Once loaded, your variables will appear in the Data Sources pane on the lower left.
Discover and Create Themes with AI
In the Data Sources tree, find a Text or Text - Multi variable set, denoted by an "A" icon:
Select the text variable you want to classify, then click + > Text Categorization.
- If you want to classify responses into multiple themes, select Multiple themes.
- If you want to classify responses into a single theme, then select Only one theme.
Then click Start.
If you're not sure which option is best for the text data you're working with, see Finding the Best Text Analysis for Your Data for examples.
The Text Categorization module will open. You have the original text responses on the right:
Click to put the AI to work creating themes based on your text input data. By default, it'll create 10 themes, but you can change this as you like.
Once Displayr has created the themes, you will see something similar to the one below. Notice the themes have appeared on the left.
Take things even further using AI. Use AI-based custom prompts to enhance the quality and relevance of your themes. See Optimizing Text Categorization with Custom Prompts for more information.
Classify Responses with AI
To classify your text data into the themes, click the button. When it's done, you'll see which themes each response has been classified into - the colored triple letters match the themes on the left.
It's always a good idea to check the classified data to ensure everything looks sensible. You can also check out Improving the Quality of Your Text Analysis Classifications for tips and the steps to perform a quality check. For a full overview of how the Text Categorization module works, along with its other smart-searching features, see How to Classify Text Data.
Another opportunity to improve text classification is to use AI-based custom prompts for classification. See Optimizing Text Categorization with Custom Prompts for more information.
Save Your Classifications
Once you're happy with the classification, click Save in the bottom-right corner. This will take you back to Displayr's main Edit mode interface. A new classified variable set will appear in the Data Sources tree next to your original text variable and have "Categorized" in the name.
It will have an icon with two radio buttons (Nominal structure) if you selected Only one theme, or an icon with two boxes (Binary - Multi structure) if you selected Multiple themes when you started the process. You can read more about Displayr's variable set structures here.
You can also share/export a file of the code frame (i.e., what responses make up each category) to use in the Text Categorization module to classify other text variables, see the individual reusing and exporting a code frame articles for more details.
Report on Your Classifications
You can create summary tables or crosstabulations using your classified variable set. You can also create custom outputs and visualizations.
How To Make a Summary Table or Crosstab
Select the new variable and drag it onto the Page to create a summary table.
To create a crosstab, drag another variable into the Columns of the summary table, like this:
How To Make a Visualization
Select a table and in the object inspector, click Visualization. A visualization menu will appear where you can select your desired visualization type.
How to Share a Report
Once you've built your report, Displayr makes it easy to share as an online dashboard or export to PowerPoint, PDF, or Excel. Check out the Share button in the upper right corner for options. See How to Publish a Document as a Web Page (Dashboard) and Publishing to Excel, PowerPoint, and as a PDF for more details.
Next
Frequently Asked Questions about Text Analysis
Improving the Quality of Your Text Analysis Classifications
Finding the Best Text Analysis for Your Data