NCBI Bookshelf. A service of the National Library of Medicine, National Institutes of Health.
Paynter R, Bañez LL, Berliner E, et al. EPC Methods: An Exploration of the Use of Text-Mining Software in Systematic Reviews [Internet]. Rockville (MD): Agency for Healthcare Research and Quality (US); 2016 Apr.
EPC Methods: An Exploration of the Use of Text-Mining Software in Systematic Reviews [Internet].
Show detailsThe following databases were searched:
- SRC Methods Library
- Inspec
- LISA via ProQuest
- Science Citation Index
- Social Sciences Citation Index via Web of Knowledge
- Library, Information Science & Technology Abstracts (LISTA) via EBSCO
- HTAIvortal http://vortal.htai.org/?q=about/sure-info
- Google Scholar
- IEEE
- PubMed (in process materials search)
- PsycINFO
- Cochrane Library
Other online sources searched were:
- NacTEM website
- Research Synthesis Methods TOC
- PLOS text-mining collection: http://www.ploscollections.org/article/browseIssue.action?issue=info:doi/10.1371/issue.pcol.v01.i14
- ACM digital library
The search syntax used in the database searches was tested in Embase.com. A sensitive search strategy was used in the title, abstract, and keyword fields (where available).
| Text-mining | EMTREE ‘Machine learning’/exp Ultimate parent is ‘information processing’/exp | Literature mining Text mining Text analysis Machine NEAR/2 learning (document OR Text) NEAR/2 (classif* OR cluster* OR characteri* OR categoriz*) ‘support vector machine’ SVM Cluster NEAR/2 tool* |
|---|---|---|
| MeSH Exp artificial intelligence/ | ||
| Natural language processing | EMTREE ‘natural language processing’:de | ‘Natural language processing’ NLP ‘Term recognition’ ‘Word frequency analysis’ |
| MESH Included under artificial intelligence along with support vector machines | ||
| EMTREE ‘information retrieval’ | (information OR knowledge OR text) NEAR/2 visual* ‘objectively derived’ Summarization ‘text retrieval’ ‘visual data exploration’ automat* Semi NEAR/1 automat* Active learning Citation management Review management (article* OR citation* OR document*) NEAR/2 (identif* OR retrieval* OR screen*) | |
| MeSH Cluster analysis ‘Information storage and retrieval’ | ||
| Specific tools | ‘Abstrackr’ ‘Aquad’ ‘carrott2’ ‘cassandre’:ti,ab ‘coding analysis toolkit’ ‘computer aided textual markup & analysis’ ‘EPPI-Reviewer 4’ ‘FreeQDA’ ‘Konstanz Information Miner’ ‘KH Coder’ ‘LibreQDA’ ‘linguamatics’ ‘Machine Learning for Language Toolkit’ ‘medsum’ ‘NLM Medical Text Indexer’ ‘Pubhub’ ‘Pubnet’ ‘PubReMiner’ ‘QCAmap’ ‘QDA Miner Lite’ ‘Qigga’ ‘RQDA’ ‘SAS on demand’ ‘Semantic Features In Text’ ‘SIDER 2’ ‘Text analysis markup system’ ‘text mining infrastructure in R’ ‘Weft QDA’ ‘WordStat’ ‘Termine’ ‘Carrot Lingo 3G’ ‘Bibexcel’ ‘Voyant’ | |
| Systematic review | ‘systematic review (topic)’ ‘systematic review’ ‘meta analysis’ ‘meta analysis (topic)’ | systematic NEAR/2 review* (evidence OR research OR comprehensive) NEAR/2 (synthes* OR review) ‘Meta analysis’ Meta-analysis |
| Methods | Method* Technique* Algorithm* |
Limits: 2005-2015, English language
| Set Number | Concept | Search Statement | # Identified |
|---|---|---|---|
| 1 | Text-mining | ‘machine learning’/exp OR (machine NEAR/2 learning) | 71,160 |
| 2 | (‘literature’ OR ‘text’) NEAR/2 mining | 1,595 | |
| 3 | (document OR text) NEAR/2 (classif* OR cluster* OR characteri* OR categoriz*) | 606 | |
| 4 | ‘support vector machine’:de OR ‘support vector machine’ OR ‘SVM” | 11,271 | |
| 5 | Cluster* NEAR/2 tool* | 248 | |
| 6 | #1 OR #2 OR #3 OR #4 OR #5 | 75,134 | |
| 7 | Natural language processing | ‘natural language processing’:de OR ‘natural language processing’ OR ‘NLP’ OR ‘term recognition’ OR ‘word frequency analysis’ | 2,876 |
| 8 | Combine sets | #6 OR #7 | 77,011 |
| 9 | Potential uses | ‘information retrieval’:de | 16,708 |
| 10 | (information OR knowledge OR text) NEAR/2 visual* | 7,341 | |
| 11 | ‘objectively derived’ OR summarization OR ‘text retrieval’ OR ‘visual data exploration’ OR ‘visual data representation’ OR ‘data abstraction’ | 1,428 | |
| 12 | Automat* OR (semi NEAR/2 automat*) | 136,711 | |
| 13 | (citation OR review) NEAR/2 manag* | 6,575 | |
| 14 | (article* OR citation* OR document*) NEAR/2 (identif* OR retrieval* OR screen*) | 13,197 | |
| 15 | #9 OR #10 OR #11 OR #12 OR #13 OR #14 | 177,247 | |
| 16 | Systematic reviews | ‘systematic review’:de OR ‘systematic review (topic)’:de | 94,565 |
| 17 | Systematic NEAR/2 review* | 123,057 | |
| 18 | (evidence OR research OR comprehensive OR critical OR Cochrane) NEAR/2 (synthes* OR review*) | 70,436 | |
| 19 | ‘meta analysis’:de OR ‘meta analysis (topic)’:de OR (meta NEAR/1 analy*) | 109,864 | |
| 20 | Combine sets | #16 OR #17 OR #18 OR #19 | 225,345 |
| 21 | Limiting concepts | #20 AND (method* OR technique* OR algorithm*) | 123,113 |
| 22 | Combine sets | #8 AND #15 AND #21 | 140 |
| 23 | Specific programs | ‘Abstrackr’ OR ‘Aquad’ OR ‘carrott2’ OR ‘cassandre’:ti,ab OR ‘coding analysis toolkit’ OR ‘computer aided textual markup & analysis’ OR ‘EPPI-Reviewer 4’ OR ‘FreeQDA’ OR ‘Konstanz Information Miner’ OR ‘KH Coder’ OR ‘LibreQDA’ OR ‘linguamatics’ OR ‘Machine Learning for Language Toolkit’ OR ‘medsum’ OR ‘NLM Medical Text Indexer’ OR ‘Pubhub’ OR ‘Pubnet’ OR ‘PubReMiner’ OR ‘QCAmap’ OR ‘QDA Miner Lite’ OR ‘Qigga’ OR ‘RQDA’ OR ‘SAS on demand’ OR ‘Semantic Features In Text’ OR ‘SIDER 2’ OR ‘Text analysis markup system’ OR ‘text mining infrastructure in R’ OR ‘Weft QDA’ OR ‘WordStat’ OR ‘Termine’ OR ‘Carrot Lingo 3G’ OR ‘Bibexcel’ OR ‘Voyant’ | 213 |
| 24 | Combine sets | #21 AND #23 | 6 |
| 25 | Combine sets | #22 OR #24 | 146 |
- Search Strategies - EPC Methods: An Exploration of the Use of Text-Mining Softwa...Search Strategies - EPC Methods: An Exploration of the Use of Text-Mining Software in Systematic Reviews
Your browsing activity is empty.
Activity recording is turned off.
See more...