Create beginner Works with: Any AI

Survey Question Bias Review

Before after Has example

Fix leading, loaded, and double-barreled questions.

The Open buttons send the prompt text as currently shown below to that site only when you click. Fill in the placeholders first.

Review survey questions for bias. Draft questions: [DRAFT_QUESTIONS]. Audience: [AUDIENCE]. Goal: [GOAL].

For each question identify problems: leading wording, loaded terms, double-barreled (two ideas in one), vague time frames, unbalanced scales, missing options (no "not applicable"), assumptions about the respondent, jargon, sensitive questions without an opt-out, and order effects. Rewrite each question with the fix and explain the reason.

Return a table: Original | Problem | Revised question | Response options | Reason. Example: Original "How much do you love our easy-to-use app?" Revised "How easy or difficult was it to complete your last order in the app?" with a 5-point scale from very difficult to very easy.

Add a review of the whole survey: length, order (easy to hard, sensitive last), logic, and respondent burden estimate (about 5 to 8 seconds per simple question). Provide a pilot test plan with five people. Do not change the research goal; ask if it is unclear.

Fill in before use

Optional: type your details and the prompt above updates. Nothing is saved or sent.

Replace each bracketed placeholder with your own details, then paste into Any AI or another assistant.

Original: "How much do you love our easy-to-use app?" Problems: leading, loaded, double-barreled (love, easy). Revised: "How easy or difficult was it to complete your last order in the app?" Options: very difficult, difficult, neither, easy, very easy.
Original: "Do you agree that our prices are fair and our service is excellent?" Problem: two ideas and agreement bias. Revised: two items: "How fair are our prices?" and "How would you rate our service?"
Original: "How often do you shop with us?" Problem: vague time frame. Revised: "In the last 3 months, how many times did you order?"
Burden: 12 questions x about 8 seconds = 96 seconds plus 2 open questions at 45 seconds = 186 seconds, about 3 minutes.
Order: easy first; sensitive last. Pilot with five people.

• survey-bias