Abstract: A collaboration platform facilitates review of research papers by recommending papers to reviewers and managing annotation of the papers by the reviewers. The platform applies a model to analyze historical actions by a user with respect to the platform to predict an attribute of the user. Based on a match between the predicted attribute and the subject matter of a paper, the platform recommends at least one research paper to the user. As the user reads the paper, the platform receives an input from the user to define an annotation associated with the research paper. The user attribute is linked to the annotation and the annotation is published in association with the research paper, where the annotation is selected for display to a second user based at least in part on the attribute of the user.

Abstract: A computer system generates a first rating of a research paper by applying one or more trained machine learning models to data extracted from the research paper. As one or more users interact with the research paper, the computer system detects actions by the user that are directed to the research paper. The computer system modifies the one or more machine learning models using the actions by the users. A second rating of the research paper is generated by applying the modified models to the actions by the users and the first rating of the research paper.