Coauthorship Network Mining for Scholar Communication and Collaboration Path Recommendation

With the increasing penetration of interdisciplinary subjects, it is more difficult for researchers to complete a paper individually, showing that the division of labor can improve the level and efficiency of scientific research. Thus, collaboration among multiple scholars has become a trend in acad...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Weiting Zhao, Zheng Zou, Zidong Wei, Wenwen Gong, Chao Yan, Ashish Kr Luhach
Formato: article
Lenguaje:EN
Publicado: Hindawi-Wiley 2021
Materias:
Acceso en línea:https://doaj.org/article/598b1c8c9a504e5f9152039173d9b6fc
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
Descripción
Sumario:With the increasing penetration of interdisciplinary subjects, it is more difficult for researchers to complete a paper individually, showing that the division of labor can improve the level and efficiency of scientific research. Thus, collaboration among multiple scholars has become a trend in academic research. However, because the numbers of scholars and papers are increasing and cooperation between scholars has become more frequent in recent years, it is an increasingly challenging task to discover useful knowledge resources for researchers. Against the background of big data, how to help scholars quickly find interested target collaborators, encourage them to participate more actively in academic communication, and create high-quality achievements in scientific research has become a significant problem. Considering this challenge, this article proposes a framework of coauthorship strength, author contribution, and search (CCS,taking the first letter of the keyword), which is based on the coauthorship feature of Google Academics. In CSS, we combined the search algorithm to select the optimal connection path to help scholars find interested target scholars efficiently and to better solve practical application problems. Finally, our proposal is evaluated by a set of experiments based on a real-world dataset. Experimental results of our approach show better search outcomes compared to other competitive approaches.