Embedded Files
AI-TRACE
CNPq/MCTI/FNDCT Nº 22/2024 - Programa Conhecimento Brasil
Grant #444933/2024-7
(December 27, 2024 -- December 31, 2026)
CNPq/MCTI/FNDCT Nº 22/2024 - Programa Conhecimento Brasil
Grant #444933/2024-7
(December 27, 2024 -- December 31, 2026)
Online disinformation can have harmful effects on society, impacting public health, economy, politics, among others. Research to analyse, detect, or predict online disinformation has received high attention in recent years, although models addressing the inherently multimodal and temporal aspects of disinformation are still scarce. The AI-TRACE project fills this gap by focusing on multimodal and temporal AI-driven models that can perform analysis in large data streams with disinformation as a use case.
Team
Diego Furtado Silva (coordinator) (University of São Paulo)
Carolina Evaristo Scarton (University of Sheffield)
Jefersson Alex dos Santos (University of Sheffield)
Leo Sampaio Ferraz Ribeiro (University of São Paulo)
Renato Moraes Silva (University of São Paulo)
Ricardo Marcondes Marcacini (University of São Paulo)
Thiago Alexandre Salgueiro Pardo (University of São Paulo)
A joint initiative of the University of São Paulo and the University of Sheffield for a more real world
Related publications
Lucca Baptista Silva Ferraz, Jhúlia de Souza Leal, Anderson Raymundo Avila, Thiago Alexandre Salgueiro Pardo, Fernando Batista, Renato Moraes Silva. Retrieval-Augmented Generation with Small Language Models for Fake News Detection. PROPOR 2026: 17th International Conference on Computational Processing of Portuguese. Link: https://drive.google.com/file/d/1xY63qk10ukqpTSI2IBsivNbfS_BfmMNB/view?usp=sharing
Pedro Lucas Castro de Andrade, Renato Moraes Silva, Thiago Alexandre Salgueiro Pardo. Caracterização lexical e sintática de notícias falsas em português produzidas por humanos e por máquinas. The Third Student Research Workshop (SRW) at the 17th International Conference on Computational Processing of Portuguese (PROPOR 2026). Salvador, BA, Brazil, April 2026, pp. 1–11.
Manuela Guedes Wanderley; Lucca Baptista Silva Ferraz; Tiago Agostinho Almeida; Renato Moraes Silva. A Moving Target: Detecting Concept Drift in Brazilian Portuguese Fake News. Proceedings of the 16th Symposium in Information and Human Language Technology (STIL’2025), Fortaleza–CE, Brasil, p. 490–501, set./2025. SBC, Porto Alegre, RS, Brasil. Link: https://doi.org/10.5753/stil.2025.37849. Honorable Mention Award.
Renato Moraes Silva; Hazem Amamou; Lucca Baptista Silva Ferraz; Fabio Kauê Araujo da Silva; Anderson Raymundo Avila. Fake News Detection in Portuguese Under Large Language Model-Generated Content. Journal of the Brazilian Computer Society, v. 31, n. 1, p. 1150–1167, out./2025. Link: https://doi.org/10.5753/jbcs.2025.5525.
Camila Aya Saito, Renato Moraes Silva. 33º Simpósio Internacional de Iniciação Científica e Tecnológica da USP. Base de Dados de Vı́deos Curtos para Detecção de Desinformação em Português. ISSN: 2448-072X. Link: https://uspdigital.usp.br/siicusp/siicPublicacao.jsp?codmnu=7210
Lucca Baptista Silva Ferraz; Renato Moraes Silva. 33º Simpósio Internacional de Iniciação Científica e Tecnológica da USP. Retrieval-Augmented Generation para classificação de notícias em cenário de desvio de conceito. ISSN: 2448-072X. Link: https://uspdigital.usp.br/siicusp/siicPublicacao.jsp?codmnu=7210
Page updated
Report abuse