Academic rising star prediction via scholar’s evaluation model and machine learning techniques

Predicting future academic rising stars provides a useful reference for research communities, such as offering decision support to recruit young researchers in research institutes. Academic rising stars prediction is considered to be a classification or regression task in the field of machine learning. Traditional methods of building label information for this task are only based on the increment of citation count, which cannot adequately reflect the evolution of a scholar’s academic influence. In this paper, we first propose a non-iterative hierarchical weighted evaluation model based on the quality of citing papers and the influence of co-authors. Second, we label each young scholar by the increment of the impact score from our evaluation model in the classification task, aiming at better describing the change of a scholar’s impact from more angles. Finally, different groups of features that can determine if a scholar will be a rising star are extracted, and various classification models are utilized to fit the classification relationships. The experimental results on the ArnetMiner dataset verify the feasibility of the prediction task based on our label construction method. We also find that the venue features are the best indicators for rising stars prediction in our experiments.