Brazilian scientific productivity from a gender perspective during the Covid-19 pandemic: classification and analysis via machine learning

Abstract

Scientific research activities, in general, have been affected due to the COVID-19 pandemic and the need for distancing. In this paper, an analysis of the impact of COVID-19 on Brazilian scientific research is made, examining the number of complete manuscripts published in the period from 2018 to 2021, considering the researcher's gender. A crawler is implemented to extract the names of Brazilian researchers from the articles, and some machine learning models (SVM, BiLSTM, and CNN) are applied to classify the authors' gender. Some models are able to accurately predict gender in more than 95% of cases. In addition, we verified that in 2021 there was a drop of 37.47% in the publications of articles by Brazilian researchers. The results indicate that there was a greater drop in publications for females in most machine learning models applied, corroborating differences in the distribution of household activities and family care between the two genders.