Analysis of Predicting Co-Authorship Networks Using Support Vector Machine Model

Authors

Mohammed Y. Al-khuzaie, College of Nursing, National University of Science and Technology, Dhi Qar, IraqFollow
Sajad Ali Zearah, Republic of Iraq Ministry of Agriculture, Thi-Qar, Outside North America, IraqFollow
Abbadullah H. Saleh, Graduate School of Natural and Applied Sciences, Gazi University, Ankara, TurkeyFollow

Abstract

The area of computer science is flourishing, as shown by the rising number of academic works published and the rising number of scholars adding to the existing body of knowledge. This has made it difficult to find previously unrecognized links between publications and those studying them. Using machine learning techniques to foresee missing links and unveil hidden connections, complex network-based link prediction has emerged as a helpful resource in addressing this difficulty. This study aims to solve the problem of finding links between authors’ publications by exploring the use of network-based complex link prediction approaches. A large-scale bibliographic database collected from various reliable sources, including but not limited to Google Scholar, was used. A Support Vector Machine (SVM) classifier was used to predict the possibility of a new link between an author and his publication. Accuracy was one of the several criteria used to evaluate the performance of the SVM classifier, which was relatively high at 96.66%.

Recommended Citation

Al-khuzaie, Mohammed Y.; Zearah, Sajad Ali; and Saleh, Abbadullah H. (2024) "Analysis of Predicting Co-Authorship Networks Using Support Vector Machine Model," AUIQ Technical Engineering Science: Vol. 1: Iss. 1, Article 9.
DOI: https://doi.org/10.70645/3078-3437.1008