Congenital syphilis (CS) remains a threat to public health worldwide, especially in developing countries. To mitigate the impacts of the CS epidemic, the Brazilian government has developed a national intervention project called “Syphilis No.” Thus, among its range of actions is the production of thousands of writings featuring the experiences of research and intervention supporters (RIS) of the project, called field researchers. In addition, this large volume of base data was subjected to analysis through data mining, which may contribute to better strategies for combating syphilis. Natural language processing is a form of knowledge extraction. First, the database extracted from the “LUES Platform” with 4,874 documents between 2018 and 2020 was employed. This was followed by text preprocessing, selecting texts referring to the field researchers' reports for analysis. Finally, for analyzing the documents, N-grams extraction (N = 2,3,4) was performed. The combination of the TF-IDF metric with the BoW algorithm was applied to assess terms' importance and frequency and text clustering. In total, 1019 field activity reports were mined. Word extraction from the text mining method set out the following guiding axioms from the bigrams: “confronting syphilis in primary health care;” “investigation committee for congenital syphilis in the territory;” “municipal plan for monitoring and investigating syphilis cases through health surveillance;” “women's healthcare networks for syphilis in pregnant;” “diagnosis and treatment with a focus on rapid testing.” Text mining may serve public health research subjects when used in parallel with the conventional content analysis method. The computational method extracted intervention activities from field researchers, also providing inferences on how the strategies of the “Syphilis No” Project influenced the decrease in congenital syphilis cases in the territory.

No abstract

Attribution of authorship, the science of giving an author certain text based on its writing characteristics, is a problem with a long history. This article aims to present some feature extraction techniques for the problem of attribution and recognition of authorship in order to make it a tool for use in the Distance Education platform of the Ministry of Health, AVASUS. The relevant literature presents text analysis techniques and stylometric characteristics of various texts that allow authorship to be determined. Feature extraction will serve as the basis for research targeting AVASUS, where higher education students take courses on the platform, share their interests and thoughts in the form of messages in the forums and perform activities that require writing. on certain health topics. These written productions are the focus of applying the extraction of stylometric features for classification and recognition of authorship.

No abstract

No abstract