Mining the SCOPUS database to identify potential academic rising stars

Abstract

Academic Rising Stars are often defined as authors in the earlier years of their scientific careers who have the potential to become impactful authors in the future. Universities and research institutions would benefit greatly from identifying these Academic Rising Stars and convince them to join their research teams, because if the potential of these authors is fulfilled these could benefit the institution in terms of scientific prestige and impactful scientific production. This thesis project aims to prove if it is possible to identify these Academic Rising Stars using Machine Learning classifiers and the data that is available through Elsevier’s Scopus and SciVal APIs. Conducting a case study in the field of Clustering, it was shown that it is possible to identify these authors using the average metrics from their first five years of scientific publications, with acceptable precision and accuracy. It was shown that the best attribute to label top authors is the h5-index and the classifier which can achieve the best result is the Support Vector Machine with a radial basis function kernel. The developed methodology provides a solid framework from which research institutions can identify Academic Rising Stars in the fields they are interested in.