Scientific Publication Clustering on Autonomous Maritime Navigation to Target Scientific Communities

The aim of this paper is to present an approach to a survey of scientific publications by clustering them, using the example of papers dedicated to autonomous marine navigation. The proposed approach makes it possible to carry out the data mining technology with the following visualization of the results as a non-directed graph, comprising a set of clusters. Each cluster is a research team working on a given topic. The analysis of the data on the research teams makes it possible to imagine the ideas of the scientific groups that contribute to uncovering the problems of autonomous navigation at sea. And information analysis of the most frequent keywords and word combinations will help to define the way autonomous marine navigation is moving. The paper deals with the open source software for visualization and analysis of the linked data Gephi to perform data mining. This type of approach to reviewing scientific publications allows the interaction of the contributions of scientific teams to be visualized and analysed in a clear and open way. It also makes it possible to identify scientific groups that make a significant contribution to the range of research topics being developed. In addition, the information analysis of the most frequently used keywords and word combinations will help to identify tendencies and trends in the development of the scientific field.