Detection of offensive comments and hate speech in tweets about Brazilian politics

• Grant number: 24/17208-8
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: December 01, 2024
• End date: November 30, 2025
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Sylvia Iasulaitis
• Grantee: Luiz Henrique do Nascimento Silva
• Host Institution: Centro de Educação e Ciências Humanas (CECH). Universidade Federal de São Carlos (UFSCAR). São Carlos , SP, Brazil
• Associated research grant: 22/03090-0 - Analysis of large amounts of political data and complex networks: mining modelling and applications in Computational Political Science, AP.PNGP.PI

Abstract

The use of social media has become a common practice among Brazilian voters and politicians. Through these platforms, politicians and their supporters express their opinions and discuss topics of public interest. However, this freedom of expression has led to an increase in the dissemination of offensive comments and hate speech, encompassing negative sentiments such as homophobia, racism, misogyny, etc., resulting in severe consequences for society. Faced with this problem, the analysis of offensive comments and hate speech within the scope of Brazilian politics is extremely relevant to identify patterns of behavior on social networks and promote more effective actions to combat these practices. However, manually identifying and combating such practices is a challenging task, given the enormous volume of texts published daily. Therefore, it is essential to rely on algorithms capable of detecting and dealing with this type of discourse. Given this context, this project aims to explore techniques/algorithms that allow identifying offensive comments and hate speech in tweets about Brazilian politics. This project aims to provide subsidies that contribute to other research related to socio-political phenomena, in development in the context of the FAPESP 2022/03090-0 project.