Skip to main content
WorldCist'18 - 6th World Conference on Information Systems and Technologies

Full Program »

Assessing review reports of scientific articles A Literature Review

The use of computational support has been applied in different stages for automation of the peer review process, like, reviewer assignment to the article, content’s review of the scientific article, detection of plagiarism and bias, using machine learning techniques, however, there is a lack of reviews of the studies that identify the instruments that evaluate the reviewers' comments. The main objective this systematic literature review is to find evidence about which techniques have been applied in the assessment in the reviewers' comments. Therefore, was evaluated five online data bases that identified 55 articles published since 2000 that meet the eligibility criteria of this review. The result show 6 relevant studies, which address models of assessment of scientific article reviews, only one case there was the use of machine learning identified. Our findings demonstrate that the published evidence for the effectiveness of computer-based peer review is not robust and therefore cannot be reliably used to assist reviewers automatically. We identified the need to define a set of high-quality criteria to examine the effectiveness of the review, and then automate them with the use of intelligent techniques.

Amanda Sizo
University of Coimbra
Portugal

Adriano Lino
University of Coimbra
Portugal

Álvaro Rocha
University of Coimbra
Portugal

 

Powered by OpenConf®
Copyright ©2002-2017 Zakon Group LLC