Automatic classification of informative and opinionated texts on social networks

• Grant number: 22/16511-3
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: March 01, 2023
• End date: June 30, 2024
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Helena de Medeiros Caseli
• Grantee: Leticia Bossatto Marchezi
• Host Institution: Centro de Ciências Exatas e de Tecnologia (CCET). Universidade Federal de São Carlos (UFSCAR). São Carlos , SP, Brazil
• Associated scholarship(s): 23/12267-3 - Defining textual signals to automatic classification of informative and opinionative texts on social networks, BE.EP.IC

Abstract

With the rise of the internet, new means of communication emerged or were adapted to the digital medium. In this way, the dissemination of news and the expression of personal opinions about events suffered decentralization, being published in different structures and platforms. Social networks are becoming a frequent channel for communication, but there is a lack of studies that define methods to automatically determine whether a textual publication in Portuguese is a fact or a opinion. Thus, the goal of this project is to apply Natural Language Processing (NLP) techniques in order to classify texts from Twitter as fact or opinion. Among the approaches to be investigated are: shallow machine learning, fine-tuning of pre-trained language models and multitasking learning.