Reducing workload in systematic review preparation using automated citation classification.

By AM Arjeh Cohen, William R. Hersh, K. Peterson, Po-Yin Yen. JAMIA Journal of the American Medical Informatics Association, 2006

365 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Automation of systematic literature reviews: A systematic literature review (2021, methodology): “With 219 citations, the article of Cohen et al. [33] was the article most cited.”
Graph-Sparse LDA: A Topic Model with Structured Sparsity (2014, neutral): “We consider a dataset of 1218 documents annotated with 5347 unique MeSH terms (23 average terms per document) that were screened for a systematic review of the effects of calcium-channel blocker (CCB) drugs (Cohen et al. 2006).”
Rayyan—a web and mobile app for systematic reviews (2016, methodology): “The work saved over random sampling measured at 0.95 recall (WSS@95), introduced in [16], refers to the percentage of studies that the reviewers do not have to go through because they have been screened out by the classifier at a recall of 0.95, compared to random sampling.”
Semi-automated screening of biomedical citations for systematic reviews (2010, background): “demonstrated that machine learning techniques can reduce the labor required to update systematic reviews [16].”
Using text mining for study identification in systematic reviews: a systematic review of current approaches (2015, methodology): “Cohen et al. also reported good results for a weighted model, in which they modified their voting perceptron classifier to incorporate a false negative learning rate (FNLR) [36].”