All that Glitters is not Gold: Falsely Predicted Rising Stars
Researchpedia Journal of Computing, Volume 2, Issue 1, Article 10, Pages 111-116, December 2021
Ali Daud1, Tehmina Amjad2, Tayyaba Khaliq2, and Malik Khizar Hayat3
1Department of Computer Science and Artificial Intelligence, University of Jeddah, Jeddah, Saudi Arabia
2Department of Computer Science and Software Engineering, International Islamic University, Islamabad, Pakistan
3Department of Information Technology, University of Haripur, Pakistan
Corresponding author: Tehmina Amjad (e-mail: tehminaamjad@iiu.edu.pk).
ABSTRACT Finding the rising stars in any domain is an attention-grabbing research topic these days with its significant application in various domains. Existing literature covers some methods that find the possible rising stars in domains including community question answering networks, bibliographic networks, sports networks, and telecommunication networks. Results of these methods are then used to select the competent personals for the corresponding field. Thus, these methods have great significance. Unfortunately, due to the unavailability of ground truth, the accuracy of the method and goodness to results is a challenging task. As all that glitters is not always gold, so identifying the false positive cases is equally essential. In this study, we analyze the bibliometric networks as a case study and investigated the reasons behind the falsely predicted rising stars. Less productivity and low-impact venue publications are the significant reasons of false predictions.
Keywords Finding Rising Stars, Bibliometric Networks, Machine Learning, Classification, Prediction, Academic Social Networks.
