Hope speech: modeling and validating an automatic text detection system

• Grant number: 23/10101-0
• Support Opportunities: Scholarships abroad - Research Internship - Doctorate
• Start date: November 01, 2023
• End date: October 31, 2024
• Field of knowledge: Linguistics, Literature and Arts - Linguistics - Applied Linguistics
• Principal Investigator: Waldir Beividas
• Grantee: Tulio Ferreira Leite da Silva
• Supervisor: Farah Benamara
• Host Institution: Faculdade de Filosofia, Letras e Ciências Humanas (FFLCH). Universidade de São Paulo (USP). São Paulo , SP, Brazil
• Institution abroad: Campus for Research Excellence and Technological Enterprise (CREATE), Singapore
• Associated to the scholarship: 20/15160-7 - Semiotic intelligence and Coronavirus: deep learning and speech analysis in Portuguese-Twitter, BP.DR

Abstract

The enhancement of hate speech detection and prevention could potentially be achieved through research focused on Hope Speech detection. As an alternative to content moderation, positive reinforcement has demonstrated potential in fostering a more peaceful, equitable, diverse, and inclusive society. Recent studies have observed an upsurge in the distribution of Hope Speech within YouTube comments during a period of escalated tension between two nuclear powers, Pakistan and India, hinting at a possible war. This suggests that encouraging the circulation of such positive content could contribute to tension reduction on digital social platforms. Analogous to sentiment analysis tasks, monitoring the hopes and aspirations of people also could provide valuable insights for public policy formulation. This overseas research internship proposal aims to delve into the relatively underexplored domain of Hope Speech detection, featuring some of the methodologies proposed by Professor Farah Benamara, a pioneer in the discourse turn in computational linguistics. The project also highlights the innovative and interdisciplinary approach of the DesCartes program, with an emphasis on developing hybrid artificial intelligence models for smart cities. This program is spearheaded by the Centre National de la Recherche Scientifique (CNRS) at the Campus for Research Excellence And Technological Enterprise (CREATE) in Singapore. (AU)