Fig. 1From: Text mining to support abstract screening for knowledge syntheses: a semi-automated workflowWorkflow — Phase 1: Preparation of abstracts for machine learning, and creation of the training dataset. DFMs: document feature matrices. Dark lines denote iterations. Inputs to the workflow are denoted by black boxes. Box 4a. SVD: singular value decomposition. Box 4b. LDA: latent Dirichlet allocation for topic modeling. Box 4c. Concept or word embeddings are vector representations of words and their relationships. Outputs of this workflow phase are the abstract features, as well as the screening results of the abstracts reviewed by the 2 human reviewers in order to generate the training dataset, denoted by the gray boxBack to article page