A support system for selection of reviewers

In this paper we deal with a reviewer assignment problem and as a solution we propose a decision support system which is able to recommend relevant reviewers to evaluate grant proposals as well as manuscripts. The system is composed of a user interface and three modules responsible for data transformation into information and knowledge. Firstly, a data acquisition module collects data concerning researchers. Next, an information retrieval module builds researchers´ profiles using various machine learning methods for keyword extraction, information classification and disambiguation. Finally, a recommendation module generates a ranking of potential reviewers based on a cosine similarity measure between researchers´ profiles and a problem that has to be reviewed. The system is meant to work autonomously, without any manual adjustment. It is available for free use on the Internet (http://sssr.opi.org.pl)1.