Detect common-sense negatives from search terms
Judges: A search term. Questions: noul:clearly_irrelevant_for_a_local_medical_practice - free, DIY, jobs, training, or unrelated services; choice:negative_type - exact, phrase. Action: Code adds singular and plural forms to a 'never want' list after a human skim of the batch.
AA clean typed decision (yes/no, a pick from a list, or a level on a scale) that is concrete, repeats routinely, and has meaningful value.3.85
Key facts
- Vertical
- Healthcare & dental
- Function
- Ads
- Status
- Idea
- Volume
- routine
- Value
- meaningful
- Risk
- moderate
- Evidence
- —
- Flags
- None
Build this with a classifier
Define a typed decision with a bounded answer, then evaluate it on examples.
{
"decision_type": "choice",
"question": "Does this input match the decision in “Detect common-sense negatives from search terms”?",
"input": "<input to classify>",
"output": "one label from a fixed list"
}Related use cases
Cite this
Copy a link in your preferred format.