Possible depressive profiles of university students on Facebook®: application of machine learning and natural language processing

• Grant number: 21/11395-2
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: December 01, 2021
• End date: November 30, 2022
• Field of knowledge: Health Sciences - Collective Health - Public Health
• Principal Investigator: Taís Bleicher
• Grantee: Gabriel Juvenal Reinert
• Host Institution: Centro de Educação e Ciências Humanas (CECH). Universidade Federal de São Carlos (UFSCAR). São Carlos , SP, Brazil

Abstract

With more than 3.4 billion users, social medias are integrated in the everyday life of people, being a place to express opinions, emotions and feelings. Making it, thus, excellent places to analyze the mental state of people, in a way that the use of technologies, such as Machine Learning and Natural Language Processing, allow, through user's publications, the identification of possible depressive profiles among individuals, creating opportunities for early interventions and active search. This technology is already used in some contexts, like identify emotional alteration in postpartum, correlation of Twitter posts with suicide. However, there's a lack of national and with college students use of these techniques in Brazil. This project aim to, thus, evaluate the possibility to find possible depressive profiles through college students' post in the national context. (AU)