Using complex networks and natural language processing to characterize and predict academic success

• Grant number: 20/14817-2
• Support Opportunities: Scholarships in Brazil - Doctorate
• Effective date (Start): April 01, 2021
• Status: Discontinued
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Diego Raphael Amancio
• Grantee: Ana Caroline Medeiros Brito
• Host Institution: Instituto de Ciências Matemáticas e de Computação (ICMC). Universidade de São Paulo (USP). São Carlos , SP, Brazil
• Associated scholarship(s): 22/13890-3 - Understanding the dynamics involving social media and academia, BE.EP.DR

Abstract

The understanding of scientific development helps to concentrate efforts on social and economic strategic research areas. Given this importance, Scientometrics emerged focused on using quantitative methods on academic data to explore dynamics related to publications, citations, journals, researchers, collaborations, research areas, and research institutions. Although Scientometric is not a recent study topic, only a few studies use artificial intelligence methodologies to understand and predict the academic entities' behaviors. In this project, we aim to advance the understanding of the Science of success applied to the Scientometrics field of study. We plan to study the factors that explain scientifically a well succeeded academic career. Our analysis will be centered on the dynamics involving researchers as protagonists. Using them, we will have different perspectives to understand and predict the researchers' success. The aspects of scientists' dynamics that we intend to explore are the institutional trajectory, collaborations trajectory, and virtual dynamics of the scientific community in social networks. The methodology adopted consists of the combination of complex networks and natural language processing techniques. As our main contributions, we intend to characterize successful trajectories in terms of publications, collaborations, international mobility, and other features extracted from the authors. The dissemination of publications on social networks will also be analyzed as a potential factor to characterize the researchers' success. Our research will also contribute to defining useful scientometric metrics more complex than the number of publications and citations. (AU)

Scientific publications

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

BRITO, ANA C. M.; SILVA, FILIPI N.; AMANCIO, DIEGO R.. Associations between author-level metrics in subsequent time periods. Journal of Informetrics, v. 15, n. 4, NOV 2021. (20/06271-0, 20/14817-2)