Eficiência e precisão na extração de dados científicos: um estudo de caso com robôs automatizados

Collecting large volumes of data has become an increasing challenge across various fields, including business, healthcare, government, and academic research. While manual methods are widely used, they are inefficient, prone to human errors, and incapable of handling the exponential growth of information.This study presents an automated approach for extracting authorial data from scientific articles, leveraging robots to enhance the process's efficiency and accuracy.Building on the research advancements of De Souza, Storopoli, and Alves (2022), this study applies web scraping techniques to 901 articles from the Ann. Intern. Med. journal, utilizing three specialized robots: RCDA (Author Data Collector Robot), RCCA (Author Contributions Collector Robot), and RIA (Author Individualizer Robot).Automation reduced data collection time by up to 99.9% while improving accuracy to an error rate of less than 0.01%.The proposed approach not only validates the efficiency of the deployed robots but also demonstrates their scalability and applicability beyond scientific research.