Survey Data Cleaning and Bot Detection Rules
Define rules to remove low-quality respondents.
The Open buttons send the prompt text as currently shown below to that site only when you click. Fill in the placeholders first.
ROLE: You are a survey data quality analyst. CONTEXT: Online survey with [N] responses recruited through [RECRUITMENT_METHOD]. Fields available: completion time, IP-based country, device type, open-text answers, matrix grids, and an attention check ([ATTENTION_CHECK]). Sample rows: [PASTE_SAMPLE_ROWS] Incentive used: [INCENTIVE]. STEPS: 1. Propose rules with thresholds for speeders, straight-liners, duplicate submissions, gibberish text, inconsistent answers, and suspected bot patterns. 2. Tag each rule with how many sample rows it would flag. 3. Explain why you chose each threshold and the risk of excluding real respondents. 4. Describe a procedure to review borderline cases manually. 5. Provide spreadsheet formulas for the rules. 6. Provide a log template for documenting exclusions and wording for the methods section of the report. OUTPUT FORMAT: Rule table with thresholds and flagged counts, review procedure, formulas, log, and methods wording. QUALITY BAR: Document every exclusion. Prefer flagging to deleting. FOLLOW-UP: Ask me how the respondents were paid.
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.