Using machine learning to advance synthesis and use of conservation and environmental evidence
Open accessAbstract
Article impact statement : Machine learning optimizes processes of systematic evidence synthesis and improves its utility for evidence‐based conservation.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Ready-to-use software tools implementing active learning models currently use the same classification technique to predict relevance of publications, namely support vector machines (SVM).
“ready-to-use software tools implementing such models (Abstrackr [22], Colandr [23], FASTREAD [11], Rayyan [24], and RobotAnalyst [25]) currently use the same classification technique to predict relevance of publications, namely support vector machines (SVM).”
From Performance of active learning models for screening prioritization in systematic reviews: a simulation study into the Average Time to Discover relevant records (2023) · cites this paper as [23]
The paper describes Colandr as a tool that learns from users’ relevance decisions, but identifies its relevance-ranking method as word2vec, not SVM (Abstract, page not specified in our copy). It does not establish what classification techniques the other named tools use. (LLM, conf=0.86)
Checked by a reasoning model — may be wrong.
Experimental — accuracy not yet measuredColandr, in addition to standard identification of relevant papers, enables users to define their own set of categories and subsequently performs a multi-label classification of articles based on them.
“Finally, Colandr, in addition to the standard identification of relevant papers, enables users to define their own set of categories (e.g., 'water management') and subsequently performs a multi-label classification of articles based on them (Cheng et al. 2018).”
From Artificial intelligence for literature reviews: opportunities and challenges (2024) · cites this paper as Cheng et al. 2018
The paper’s description of Colandr (p. 762, Fig. 1) says its first system ranks articles by relevance and its second predicts topic labels for each article, with users accepting or rejecting predicted categories. It does not explicitly say that users can define their own set of categories; the categories shown in the figure are examples. (LLM, conf=0.84)
Experimental — accuracy not yet measuredColandr employs a method where it identifies papers by searching for keywords that are related to a set of user-defined search terms.
“In contrast, Colandr employs a method where it identifies papers by searching for keywords that are related to a set of user-defined search terms (Cheng et al. 2018).”
From Artificial intelligence for literature reviews: opportunities and challenges (2024) · cites this paper as Cheng et al. 2018
The Abstract says Colandr uses patterns in words around search terms to estimate relevance, which supports the claim's description of using related words. But it says Colandr ranks existing search results based on users’ relevance judgments; it does not say Colandr identifies papers by searching for related keywords or that the search terms are user-defined. (LLM, conf=0.85)
Experimental — accuracy not yet measuredPriority screening via active learning has been successfully implemented in various software tools such as Abstrackr, ASReview, Colandr, EPPI-Reviewer, FASTREAD, Rayyan, RobotAnalyst, Research Screener, DistillerSR, and robotreviewer.
“Priority screening via active learning has been successfully implemented in various software tools such as Abstrackr [49], ASReview [45], Colandr [12], EPPI-Reviewer [41], FASTREAD [54], Rayyan [28], RobotAnalyst [32], Research Screener [10], DistillerSR [20], and robotreviewer [25].”
From The SAFE procedure: a practical stopping heuristic for active learning-based screening in systematic reviews and meta-analyses (2024) · cites this paper as [12]
Dynamic article recommendation is widely accepted and a range of implementations exist, although few have been rigorously tested.
“This approach is widely accepted 33 and a range of implementations exist 27, 34 , although few of them have been rigorously tested 6 .”
From revtools: An R package to support article screening for evidence synthesis (2019) · cites this paper as [34]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Glove: Global Vectors for Word Representation
Pennington, J., Socher, R., & Manning, C. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1162 · Cited by 34,071 · see citing works
Distributed Representations of Words and Phrases and their Compositionality
Mikolov, T., Sutskever, I., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1310.4546 · Cited by 24,533 · see citing works
O’Mara-Eves, A., Thomas, J., McNaught, J., Miwa, M., & Ananiadou, S. (2015) · Systematic Reviews · doi:10.1186/2046-4053-4-5 · Cited by 681 · see citing works
Living Systematic Reviews: An Emerging Opportunity to Narrow the Evidence-Practice Gap
Elliott, J. H., Turner, T., Clavisi, O., Thomas, J., Higgins, J. P. T., Mavergames, C., & Gruen, R. L. (2014) · PLoS Medicine · doi:10.1371/journal.pmed.1001603 · Cited by 596 · see citing works
Introduction to Machine Learning
Baştanlar, Y., & Özuysal, M. (2013) · Methods in molecular biology · doi:10.1007/978-1-62703-748-8_7 · Cited by 506 · see citing works
O’Mara-Eves, A., Thomas, J., McNaught, J., Miwa, M., & Ananiadou, S. (2015) · Systematic Reviews · doi:10.1186/s13643-015-0031-5 · Cited by 351 · see citing works
Bibliometric analysis of global environmental assessment research in a 20-year period
Li, W., & Zhao, Y. W. (2014) · Environmental Impact Assessment Review · doi:10.1016/j.eiar.2014.09.012 · Cited by 306 · see citing works
Doing more good than harm – Building an evidence-base for conservation and environmental management
Pullin, A. S., & Knight, T. (2009) · Biological Conservation · doi:10.1016/j.biocon.2009.01.010 · Cited by 295 · see citing works
McKinnon, M., Cheng, S. H., Dupre, S. I., Edmond, J., Garside, R., Glew, L., Holland, M. B., Levine, E. B., Masuda, Y. J., Miller, D. C., et al. (2016) · Environmental Evidence · doi:10.1186/s13750-016-0058-7 · Cited by 263 · see citing works
Self-citationText analysis tools for identification of emerging topics and research gaps in conservation science
Westgate, M. J., Barton, P. S., Pierson, J. C., & Lindenmayer, D. B. (2015) · Conservation Biology · doi:10.1111/cobi.12605 · Cited by 123 · see citing works
Using machine learning to disentangle homonyms in large text corpora
Roll, U., Correia, R. A., & Berger‐Tal, O. (2018) · Conservation Biology · doi:10.1111/cobi.13044 · Cited by 46 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
An open source machine learning framework for efficient and transparent systematic reviews
van de Schoot, R., de Bruin, J., Schram, R., Zahedi, P., de Boer, J., Weijdema, F., Kramer, B., Huijts, M., Hoogerwerf, M., Ferdinands, G., et al. (2021) · Nature Machine Intelligence · doi:10.1038/s42256-020-00287-7 · Cited by 1,157 · see citing works
revtools: An R package to support article screening for evidence synthesis
Westgate, M. J. (2019) · Research Synthesis Methods · doi:10.1002/jrsm.1374 · Cited by 261 · see citing works
Artificial intelligence for literature reviews: opportunities and challenges
Bolaños, F., Salatino, A., Osborne, F., & Motta, E. (2024) · Artificial Intelligence Review · doi:10.1007/s10462-024-10902-3 · Cited by 246 · see citing works
“Finally, Colandr, in addition to the standard identification of relevant papers, enables users to define their own set of categories (e.g., “water management”) and subsequently performs a multi-label classification of articles based on them [60].”
Boetje, J., & van de Schoot, R. (2024) · Systematic Reviews · doi:10.1186/s13643-024-02502-7 · Cited by 146 · see citing works
“Priority screening via active learning has been successfully implemented in various software tools such as Abstrackr [49], ASReview [45], Colandr [12], EPPI-Reviewer [41], FASTREAD [54], Rayyan [28], RobotA-nalyst [32], Research Screener [10], DistillerSR [20], and robotreviewer [25].”
MethodFerdinands, G., Schram, R., de Bruin, J., Bagheri, A., Oberski, D. L., Tummers, L., Teijema, J. J., & van de Schoot, R. (2023) · Systematic Reviews · doi:10.1186/s13643-023-02257-7 · Cited by 96 · see citing works
“While previous studies have evaluated active learning models in many forms and shapes [10–15, 17–19], ready-to-use software tools implementing such models (Abstrackr [22], Colandr [23], FASTREAD [11], Rayyan [24], and RobotAnalyst [25]) currently use the same classification technique to predict relevance of publicatio…”
MethodCierco Jimenez, R., Lee, T., Rosillo, N., Cordova, R., Cree, I. A., Gonzalez, A., & Indave Ruiz, B. I. (2022) · BMC Medical Research Methodology · doi:10.1186/s12874-022-01805-4 · Cited by 85 · see citing works
Active learning for screening prioritization in systematic reviews - A simulation study
Ferdinands, G., Schram, R., de Bruin, J., Bagheri, A., Oberski, D. L., Tummers, L., & van de Schoot, R. (2020) · doi:10.31219/osf.io/w6qbg · Cited by 51 · see citing works
Burgard, T., & Bittermann, A. (2023) · Zeitschrift für Psychologie · doi:10.1027/2151-2604/a000509 · Cited by 29 · see citing works
GIUSTI, E. M., SPATOLA, C. A., BRUNANI, A., KUMBHARE, D., ORAL, A., ILIEVA, E., KIEKENS, C., PIETRABISSA, G., MANZONI, G. M., IMAMURA, M., et al. (2020) · European Journal of Physical and Rehabilitation Medicine · doi:10.23736/s1973-9087.20.06232-2 · Cited by 25 · see citing works
Munro, N. R., Teague, S., Somoray, K., Simpson, A., Budden, T., Jackson, B., Rebar, A., & Dimmock, J. (2026) · British Journal of Sports Medicine · doi:10.1136/bjsports-2025-110301 · Cited by 23 · see citing works
Giusti, E. M., Spatola, C. A. M., Brunani, A., Kumbhare, D., Oral, A., Ilieva, E., Kiekens, C., Pietrabissa, G., Manzoni, G. M., Imamura, M., et al. (2020) · The Journal of the International Society of Physical and Rehabilitation Medicine · doi:10.4103/jisprm.jisprm_6_20 · Cited by 2 · see citing works
Keep a Human in the Machine and Other Lessons Learned from Deploying and Maintaining Colandr
Cheng, S., & Augustin, C. (2021) · CHANCE · doi:10.1080/09332480.2021.1979818 · Cited by 2 · see citing works
Self-citation
- Authors
- Cheng, S. H., Augustin, C., Bethel, A., Gill, D., Anzaroot, S., Brun, J., DeWilde, B., Minnich, R. C., Garside, R., Masuda, Y. J., Miller, D. C., Wilkie, D., Wongbusarakum, S., & McKinnon, M. C.
- Affiliations
- University of California, Santa Barbara (US)
- DataKind (US)
- University of Exeter (GB)
- Conservation International (US)
- The Nature Conservancy (US)
- University of Illinois Urbana-Champaign (US)
- Wildlife Conservation Society (US)
- University of Hawaiʻi at Mānoa (US)
- Vulcan (United States) (US)
- Corresponding author
- Cheng, S.H.
- ORCID
- Venue
- Conservation Biology
- Publisher
- Wiley
- Published
- 2018-07-10
- Volume
- 32
- Issue
- 4
- Pages
- 762-764
- ISSN
- 0888-8892 (ISSN-L)
- 1523-1739
- OpenAlex
- W2797780449
- Cited by
- 155
- References
- 11
- Citations by year
- 2026: 9 · 2025: 24 · 2024: 32 · 2023: 18 · 2022: 11 · 2021: 25 · 2020: 25 · 2019: 5 · 2018: 6
- FWCI
- 11.61
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- Conservation Biology (publishedVersion, other-oa)
- PubMed (publishedVersion)
- Figshare (submittedVersion)
- Open Research Exeter (University of Exeter) (submittedVersion, other-oa)
- Funders
- National Institute for Health Research
- Topics
- Social Sciences › Decision Sciences › Statistics, Probability and Uncertainty › Meta-analysis and systematic reviews
- Physical Sciences › Computer Science › Information Systems › Research Data Management Practices
- Social Sciences › General Social Sciences › Computational and Text Analysis Methods
- Keywords
- machine learning, evidence-based conservation, environmental evidence, conservation evidence
- MeSH terms
- Machine Learning, Algorithms, Conservation of Natural Resources
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
