Response Quality uses machine learning to scan your survey results and flag poor-quality responses. For example, if a respondent fills a comment box with gibberish or answers option A on every question, we flag the response so you can focus on high-quality survey data.
To view the Response Quality status, the survey must be in English, and the response status must be complete.
Response Quality isn't available if:
Response Quality is on by default and analyzes responses from all open-ended questions in your survey. If you turn it off, quality flags are removed from any text responses in your survey.
Once your responses are scanned, you can scroll through Individual responses to find responses flagged as Poor quality.
If you think that we’ve incorrectly flagged a response, select Remove flag to clear the flag and flag type. This correction also helps improve flagging accuracy in the future.
To turn Response Quality on or off:
Our machine learning models are trained to look for several different types of poor-quality survey responses:
| Flag Type | Description |
| Profanity | The survey response includes a curse word. |
| Straight-lining | Multiple questions have been quickly responded to with the same answer option. For example, the respondent chose option B for every question. |
| Matrix pattern | The respondent answered a matrix question in a pattern. For example, the respondent chose option A for row 1, option B for row 2, option A for row 3, and so on. |
| Speeding | The respondent spent less time on a page than expected. We use a typical reading speed to calculate the average time a respondent should spend on a page. |
| Gibberish | The response includes a text response primarily made of nonsensical words, like "asdfjkl". |
| Length | The response is significantly shorter than other responses. |
| Not a full word | The response includes a 1-character answer that's not a word. |
| Copy-pasted answer | The response matches the question text. |
When you export a CSV, XLS, or SPSS file, your flagged responses appear in a separate file. Your Response Quality file shows the respondent ID and flag types for responses identified as Poor.
You can also use the Response Quality filter to view responses marked as poor-quality.
If you’re a Contribute or Rewards respondent and your complete response is flagged as poor-quality, you aren’t able to collect a reward or earn credits for taking the survey.