Automatic Author Profiling of Nobel Prize Winners Using 1D-CNN

The correlation between age and creativity, identified as one of the most significant scientific revelations of the twentieth century, displays more variability over time than across different areas of expertise. Conversely, factors specific to each field, such as the prevalence of theoretical approaches, educational achievements, and citation patterns, exhibit strong associations with the dynamics of the age-creativity relationship in various disciplines.In the realm of Deep Learning, there has been a rapid expansion, with widespread applications across diverse domains. This paper introduces a Deep Learning model, specifically the proposed One-Dimensional Convolutional Neural Network (CNN) model and its associated training methodologies. The dual contributions of this research to the age and innovation discourse are twofold: firstly, it conducts a comprehensive analysis encompassing all Nobel Prizes in physics, chemistry, and medicine awarded from 1901 to 2008. Secondly, by leveraging Deep Learning methods, the study aims to construct CNN models whose training involves optimizing the classification of subjects related to Nobel Laureates.The experimental results reveal that the proposed 1D-CNN demonstrates impressive performance metrics, with accuracy, F1-Score, and Precision values reaching 90.47%, 92%, and 96%, respectively.