Protocol
Split the question into a few search concepts
Search engines need concepts, not your entire internal monologue.
When it fits
- A long natural-language search returns a noisy mix of words from the whole question.
When to avoid it
- Over-decomposition can remove relevant records; keep only concepts essential to eligibility.
Why it matters
Extract the few concepts that determine relevance, then search each with its own synonyms. Combine synonyms within a concept with OR and combine the core concepts with AND where the search system supports it. Start broad enough to learn the field's terminology before adding extra constraints.
Steps
- The query logic can be explained as a small set of concepts rather than a sentence full of incidental words.
An example
For AI reliance research, separate human reliance, AI confidence/uncertainty and decision performance instead of searching a paragraph about 'trust in ChatGPT.'
Check your result
The query logic can be explained as a small set of concepts rather than a sentence full of incidental words.
Keep this limit in mind
- Over-decomposition can remove relevant records; keep only concepts essential to eligibility.
Connected ideas
Use beforeBuild a terminology map before optimizing the query
Evidence and sources
Cochrane recommends keeping the number of search concepts limited while using a wide variety of search terms combined with OR within each concept.
This is designed for sensitive review searches; ordinary research may accept lower recall for speed.
Chapter 4: Searching for and selecting studies · Key points and search strategy structure