Reviewer Assignment Decision Support in an Academic Journal based on Multicriteria Assessment and Text Mining

Abstract

Reviewer assignment to papers is one of the most significant stages of the scientific publishing process. It determines whether high-quality scientific papers are accepted for publication, while low-quality papers are rejected or sent to be improved to the required level. This in turn affects the status of academic journals and the level of scientific papers in general. A large number of researchers deals with issues of improving and speeding up of the reviewer assignment procedure, frequently using intellectual methods. However, insufficient attention is given to comprehensive reviewer assessment in their assignment to papers. A method of reviewer assignment decision support in an academic journal based on a joint use of multicriteria assessment and text mining is proposed in the paper. Calculation of an integral indicator with the use of additive folding of weighted reviewer’s indicators is at the core of the method. Text mining of manuscripts and reviewer’s papers is utilized to determine value of one of significant indicators. The proposed method allows to assess reviewers not only by authority and expertise, but also allows to take into account their work in the role of a reviewer, deciding how good they are in this role, with the use of previously collected statistical information refers to the carried out reviewing. The method has been successfully tested on data of peer-reviewed academic journal "Modeling, Optimization and Information Technology".