Figure 1.

Overview of LitSuggest. LitSuggest trains ensemble learning models based on a set of example articles from users (1). The model is then used to rank and classify new publications (2). Classified publications can then be curated (3) and shared with other users. The curation interface displays the probability score (a) for each publication, publication content (b) such as title, abstract, type, keywords, journal, date, authors, links to external resources, and interface to annotate the publication with custom tags (c), a custom text note (d) and the date and user which made the latest changes (e).