Quality model for classification of the review of scientific articles

Maintaining the quality control of scientific literature is one of the main characteristics of the peer review process. However, it depends on the peers' effectiveness in minimizing the intrinsic subjectivity to the process. Publishers try to achieve this through training and guides for reviewers. However, there is no consensus as to what the main criteria for a good review are, which results in poorly reasoned or vague reports that do not assist the editor in his decision nor the author in improvement of research. This project proposes a quality model for reviewing articles and a framework for their automatic classification through machine learning techniques. This proposal will be useful for: i) reviewers as a guideline for the preparation of the review report, ii) editors as an indicator of the quality of the received revisions, and iii) the authors as a model for self-evaluation of their research.