Build structured Boolean search strings

Generate precise Boolean search strings using keywords, synonyms, and syntax tailored for major academic indexing databases.

You getConcept Matrix, database Strings and 3 actionable tips for refining if the search returns too…

Prompt

Prompt
Act as a specialist academic reference librarian helping a researcher construct systematic database queries.

Ask me 3 short numbered questions in one message and wait for my response before writing anything else:
1. What is your research question or core topic?
2. What are the key concepts, known synonyms, or exclusions?
3. Which specific databases are you searching (such as PubMed, Scopus, Web of Science, or IEEE Xplore)?

After I respond, build tailored search strings using standard Boolean operators (AND, OR, NOT), wildcard truncation, and phrase quoting appropriate for the selected databases.

Output format:
- Concept Matrix: A markdown table listing Concept 1, Concept 2, and Concept 3 alongside relevant keywords and MeSH/thesaurus terms.
- Database Strings: Code blocks containing copyable search strings for each specified database.
- 3 actionable tips for refining if the search returns too few or too many hits.

Example output

Example for: student researching AI diagnostic tools in pediatric oncology across PubMed and Scopus

Concept Matrix
ConceptPrimary KeywordSynonyms & Variant SpellingsControlled Terms / MeSH
Concept A: Artificial IntelligenceArtificial IntelligenceMachine learning, deep learning, algorithmic diagnosis, neural network*"Artificial Intelligence"[Mesh]
Concept B: Diagnostic ImagingDiagnosisDetection, screening, image segmentation, radiology, radiom*"Diagnostic Imaging"[Mesh]
Concept C: Pediatric CancerPediatric oncologyChild* cancer, pediatric neoplasm, childhood leukemia, pediatric tumor"Pediatrics"[Mesh] AND "Neoplasms"[Mesh]
Database Strings

PubMed

("Artificial Intelligence"[Mesh] OR "machine learning"[tiab] OR "deep learning"[tiab] OR "neural network*"[tiab]) AND ("Diagnostic Imaging"[Mesh] OR diagnos*[tiab] OR screen*[tiab] OR radiom*[tiab]) AND ("Pediatrics"[Mesh] OR child*[tiab] OR pediatric*[tiab]) AND ("Neoplasms"[Mesh] OR cancer*[tiab] OR oncolog*[tiab] OR tumor*[tiab])

Scopus

TITLE-ABS-KEY(("artificial intelligence" OR "machine learning" OR "deep learning" OR "neural network*") AND ("diagnostic imaging" OR diagnosis OR screening OR radiomic*) AND (child* OR pediatric*) AND (cancer* OR oncology OR neoplasm* OR tumor*))
Search Refinement Tips
  • If zero hits appear, remove specific subfield keywords like "radiom*" to widen the initial pool.
  • If thousands of non-pediatric clinical trials appear, enforce title-only restrictions on the pediatric concept terms.
  • Check the initial five relevant papers in Scopus and inspect their author-assigned keywords to add missing synonyms.
Written by AI from this prompt. Your results will vary.

Run this prompt in ChatGPT, Claude, or Gemini and respond to the three questions. To refine your results later, paste the search string back into the chat along with the number of search hits returned to calibrate specificity.

Make it repeatable

Keep using this prompt without pasting it in every time.

Keep exploring

More in Academic Writing & Study