Open AccessUTILIZAÇÃO DE TÉCNICAS DE APRENDIZADO DE MÁQUINA PARA A VERIFICAÇÃO DE SATISFAÇÃO E TRISTEZA
Author(s) -
Victor Gabriel Viana da Costa,
Francisco Assis da Silva,
Mário Augusto Pazoti,
Leandro Luiz de Almeida,
Camélia Santina Murgo
Publication year - 2021
Publication title -
colloquium exactarum
Language(s) - English
Resource type - Journals
ISSN - 2178-8332
DOI - 10.5747/ce.2021.v13.n4.e374
Subject(s) - sadness , psychology , affect (linguistics) , depression (economics) , computer science , applied psychology , clinical psychology , communication , anger , economics , macroeconomics
Mental illnesses are symptomatic conditions that affect both the psychological and the physical aspects of a person, which can lead to death in more severe cases. An example of these illnesses is depression, which when the treatment is done quickly improves the patient's chances of recovering. So, a quick diagnosis is essential for treatment to take place effectively. However, traditional methods make it difficult for psychology professionals to analyze data in the form of images, audio and text digitally. This work aimed to contribute with a joint application to a study to optimize the diagnosis time, providing an analysis through machine processing, analyzing images, audio and text automatically, providing the professional in the field of psychology with a report of satisfaction and sadness of the patient. The results are satisfactory with an average accuracy in the validation of the network of 72.47% in the recognition of emotions.