Evaluate Data Quality
Evaluates the quality of survey responses for potential issues
Authorizations
API key for authentication
Body
The collection of question-answer pairs to evaluate
A question and answer pair from a survey response
The name of the survey as it will appear in the Aftercare platform
A description of the survey purpose and background.
It will be used to give the AI more context around specific aspects of the survey (e.g. brand/product names, movie names, etc.)
Optional unique identifier for the survey.
Aftercare will use this to build a data model to associate questions and answers with the survey.
Optional unique identifier for a respondent's entire response to a survey.
Aftercare will use this to build a data model tie together questions and answer pairs for a single response.
Optional unique identifier for the survey response. If not provided, Aftercare will generate one.
This identifier is useful for tracking survey responses that are submitted in multiple parts or over time.
If both a responseIdentifier and aftercareResponseIdentifier are provided, Aftercare will use the aftercareResponseIdentifier.
Optional array of specific quality issues to evaluate
Types of quality issues that can be detected in survey responses.
Nonsensical
- Response lacks logical meaning or sense. Likely gibberish.Irrelevant
- Response does not address the question.Low Effort
- Respondent did not put in much effort to answer the question. Lacks detail or concrete examples.LLM Generated
- Response appears to be generated by AI.Self Duplicated
- Responses from the same respondent contain duplicated content across multiple answers. Only evaluated when multiple survey entries are provided or if a survey identifier and response identifier is provided.Shared Duplicate
- Responses contain duplicated content across different respondents for the same question. Only evaluated if survey identifiers and question identifiers are provided.
Nonsensical
, Irrelevant
, Low Effort
, LLM Generated
, Repeated Answers
, Duplicate Answers
Response
Number of quality issues detected across all survey entries
x >= 0
A score between 0 and 100 that represents the overall quality of the survey response.
The score is an average of the quality scores across all survey entries.
The lower the score, the greater the likelihood and severity of data quality issues.
0 <= x <= 100
Unique identifier for the survey response generated by Aftercare