Automatic classification of mental health disorders symptoms in posts on online social networks

• Grant number: 21/02430-9
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: June 01, 2021
• End date: May 31, 2022
• Field of knowledge: Physical Sciences and Mathematics - Computer Science
• Principal Investigator: Helena de Medeiros Caseli
• Grantee: Rafael Vinicius Polato Passador
• Host Institution: Centro de Ciências Exatas e de Tecnologia (CCET). Universidade Federal de São Carlos (UFSCAR). São Carlos , SP, Brazil

Abstract

The internet has re-signified the way in which people communicate, buy, learn, among others. In the meantime, the phenomenon of online social media (OSM) within the scope of individual freedom of expression is seen as an important tool for its users to pronounce their daily actions and, mainly, their thoughts and feelings. Concomitantly, the treatment of mental health disorders, of which depression is the best known, can be considered one of the most important mental health issues nowadays. In particular, in the university environment, the scenario chosen for study in this project, the prevalence of depression seems to be higher than in the rest of the population. Thus, RSO can be important allies to identify individuals who demonstrate a possible depressive profile (PDP), being a useful tool for the effective targeting of mental health resources. Several studies indicate that OSM are more natural environments for the identification of PDP when compared to the instruments commonly used in the health area. With the advancement of new approaches in the Mental Health sector, which enhance the identification of symptoms related to mental health disorders, the focus of this project arises: to verify how these symptoms are manifested in textual posts and to apply Natural Language Processing techniques (NLP) and Machine Learning (ML) to identify and classify them automatically. (AU)