Skipper Autocode leverages AI to automatically detect themes in your response data and code them accordingly, or to bulk-add codebooks to individual questions in your survey.

Enabling Skipper Autocode

On the Survey Editor page, when you first add an Open-Ended Question, Form Question, or Open-Ended answer option, a message will appear at the bottom of the page. Keep the box checked to leverage Skipper Autocode during your survey analysis.

If you didn't enable Autocode before launching and wish to use it, open the stats page of your survey:

1. Navigate to the Coding tab in the left sidebar.
2. Click Unlock Autocoding. You'll be redirected to the checkout page to purchase the feature.
3. After completing the purchase, Autocode will be available on the Stats page.

Using Skipper Autocode

To analyze and create codebooks using Skipper Autocode, open the Coding pane in the left menu.

1. Click the dropdown beneath Autocoding and select the desired question.
2. Click the Autocode dropdown and select Autocode.
3. Click Run autocode. Skipper will analyze all verbatim responses, create a codebook with relevant codes, and assign those codes to responses.

💡 Tip: Skipper Autocode can review open-ended responses written in any language — the resulting codes will be displayed in English.

Autocode Existing Codebooks

Allow Skipper to analyze responses and assign codes using an existing codebook, or create one manually first:

1. Click Add a new codebook, type a title, and click OK.
2. Click the dropdown beneath Autocoding and select the desired question.
3. Click the Autocode dropdown and select Apply Codebook.
4. Select the desired codebook from the Codebook dropdown.
5. Click Apply autocode.

⚠️ Note: Filtering to a question in the Autocoding pane doesn't change the view in the main Open Ends report — use the main Open Ends report dropdown to change the page view.

Guided Autocode

Use Guided Autocode to expand and refine an existing category, or create a codebook for a specific theme you want to explore for a particular question.

1. Click the dropdown beneath Autocoding and select the desired question.
2. Click the Autocode dropdown and select Guided autocode.
3. Select the desired codebook from the third dropdown.
4. Click Run Guided autocode. Skipper will compare the existing codebook structure to the responses and create a new codebook.

⚠️ Note: The new codebook may contain some of the same codes, but will also include other similar themes detected in the comparison.

Editing Existing Codebooks and Codes

Click the settings wheel to the right of any codebook or code to manage it.

Codebook options:

• Rename the codebook
• Clone codebook
• Copy codebook structure
• Delete codebook and codes from all reports

With a specific question selected from the Verbatim dropdown, two additional options appear: Apply to Q# and Run guided autocode on Q#.

Code options:

• Remove the code from comments on the page
• Remove code from all found comments
• Rename the code
• Assign to multiple comments
• Delete the code from all reports

Sentiment Analysis

LLM-powered Sentiment Analysis enables Skipper to interpret and apply sentiment to unstructured data in open-ended responses.

1. From the Results page, click the Verbatim icon to view all open-ended responses. The colored bands on the left of each comment box indicate sentiment:
   • Green (smiling face) — positive
   • Orange (unsure face) — mixed
   • Red (frowning face) — negative
   • Blue (neutral face) — neutral
   • Gray (no mouth face) — none
2. Hover inside a response to see the emoticon, then click it to view the full sentiment spectrum.
3. Click the Coding icon in the left navigation to view codebooks and sentiment codes.
4. Click the Sentiments folder to view sentiments as codes.
5. Click the gear icon on the Sentiments folder and select Rerun Sentiment Analysis to reprocess and redistribute sentiment codes. You can still adjust sentiments manually after rerunning.

⚠️ Note: To unlock LLM-powered sentiment analysis, your account must have AI and Skipper enabled. This feature is not applied retroactively to past surveys — contact our team if you'd like to apply it to a previous survey.

Learn more about Sentiment Analysis here.

Autocode in Virtual Questions

Autocode is available in Virtual Questions as a Codebook preset that automatically generates and assigns codes for efficient correlation analysis.

1. On the Results page, click the Data Lab tab in the left menu.
2. Click the Virtual Question bar to add a VQ, or drag it into place between questions.
3. Click the Optional Presets dropdown and scroll to Codebooks.
4. Select the desired codebook and click Generate Visualization.

💡 Tip: If you rename a code, it will automatically update in Virtual Questions.

Autocode in Correlation Finder

1. On the Results page, click the Data Lab tab and drag the Correlation Finder into place in your results.
2. Click the pencil icon to edit the name in the Question Header.
3. Click the dropdown and select SigTest (t/z test) or Crosstab (chi²).
4. Click Choose a banner to select a banner from demographic traits, questions, codebooks, or Virtual Questions. Use the second banner dropdown to refine your variable. The banner is the independent variable — the underlying factor that can lead to statistical significance.
5. Click Choose an attribute to select the dependent variable you're using to explore statistical significance.
6. Click Generate data. Once added, you can export the chart and data table to PowerPoint or download a static image.

💡 Tip: If you rename a code, it will automatically update in Correlation Finders.

Logic for Codes and Codebooks

Use the following logic syntax to reference codes and codebooks in filters or virtual questions:

• Single code, single question: Q1 tag = 'codebook name: code name' — same as tag Q1 = 'codebook name: code name'
• Single code, multiple questions (OR): tag Q1,Q2 = 'codebook name: code name' — the comma acts as or
• Single code, multiple questions (AND): tag Q1 = 'codebook name: code name' and tag Q2 = 'codebook name: code name'
• Codebook references follow the same structure:
  • Codebook = 'name'
  • Codebook Q1 = 'name' — same as Q1 codebook = 'name'
  • Codebook Q1,Q2 = 'name' — same as codebook Q1 = 'name' OR codebook Q2 = 'name'

⚠️ Note: For single questions, Q1 can go before or after tag. For multiple questions, it can only come after tag.

Exporting Verbatim Responses

To export by individual question:

1. Scroll to an open-ended question in your quant report.
2. Click the Export icon to open the dropdown.
3. Select Download all verbatim (CSV) or Download all verbatim with codes (CSV).

To export verbatims for the entire survey:

1. Open the Verbatim page of your stats page.
2. Click the Export icon in the left menu to open the Export Comments pane and select your desired export.

💡 Tip: To export verbatim responses with their codebook and codes, select Excel Coded Maps, Raw CSV, or Excel RAW.