André da Fonseca Schuck
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
André da Fonseca Schuck has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Alexandre Meira de Vasconcelos
Universidade Federal de Mato Grosso do Sul
1 shared publication - Felipe Cássio da Silva Caxito
Univ Fed Mato Grosso Do Sul UFMS, Engn Prod, Cidade Univ,Av Costa & Silva, BR-79070900 Pioneiros, MS, Brazil
1 shared publication - Gabriel Lino Garcia
Sao Paulo State University
1 shared publication - João Paulo Papa
São Paulo State University (UNESP)
1 shared publication - João Renato Ribeiro Manesco
São Paulo State University (UNESP)
1 shared publication - Pedro Henrique Paiola
Sao Paulo State University
1 shared publication
Latest Publications
- Open Access
- 17 January 2025
- Published by Sociedade Brasileira de Computação in Journal of the Brazilian Computer Society
- Vol. 31 (1) , 885-917
Evaluating Large Language Models for Brazilian Portuguese Sentiment Analysis: A Comparative Study of Multilingual State-of-the-Art vs. Brazilian Portuguese Fine-Tuned LLMs
This study presents an extensive comparative analysis of Large Language Models (LLMs) for sentiment analysis in Brazilian Portuguese texts. We evaluated 23 LLMs—comprising 13 state-of-the-art multilingual models and 10 models specifically fine-tuned for Portuguese—across 12 public annotated datasets from diverse domains, employing the in-context learning paradigm. Our findings demonstrate that large-scale models such as Claude-$3.5$-Sonnet, GPT-4o, DeepSeek-V3, and Sabiá-3 delivered superior results with accuracies exceeding 92%, while smaller models (7-13B parameters) also showed compelling performance with top performers achieving accuracies above 90%. Notably, linguistic specialization through fine-tuning demonstrated mixed results—significantly reducing hallucination rates for some models but not consistently yielding performance improvements across all model types. We also observed that newer model generations frequently outperformed their predecessors, and in the one dataset where traditional machine learning methods were employed by the original authors for sentiment classification, all evaluated LLMs substantially surpassed these traditional approaches. Moreover, smaller-scale models exhibited a tendency toward overgeneration despite explicit instructions. These findings contribute valuable insights to the discourse on language-specific model optimization and establish empirical benchmarks for both multilingual and Portuguese-specialized LLMs in sentiment analysis tasks.
- 17 January 2025
- Published by Sociedade Brasileira de Computação in Journal of the Brazilian Computer Society
- Vol. 31 (1) , 885-917
Open AccessEvaluating Large Language Models for Brazilian Portuguese Sentiment Analysis: A Comparative Study of Multilingual State-of-the-Art vs. Brazilian Portuguese Fine-Tuned LLMs
This study presents an extensive comparative analysis of Large Language Models (LLMs) for sentiment analysis in Brazilian Portuguese texts. We evaluated 23 LLMs—comprising 13 state-of-the-art multilingual models and 10 models specifically fine-tuned for Portuguese—across 12 public annotated datasets from diverse domains, employing the in-context learning paradigm. Our findings demonstrate that large-scale models such as Claude-$3.5$-Sonnet, GPT-4o, DeepSeek-V3, and Sabiá-3 delivered superior results with accuracies exceeding 92%, while smaller models (7-13B parameters) also showed compelling performance with top performers achieving accuracies above 90%. Notably, linguistic specialization through fine-tuning demonstrated mixed results—significantly reducing hallucination rates for some models but not consistently yielding performance improvements across all model types. We also observed that newer model generations frequently outperformed their predecessors, and in the one dataset where traditional machine learning methods were employed by the original authors for sentiment classification, all evaluated LLMs substantially surpassed these traditional approaches. Moreover, smaller-scale models exhibited a tendency toward overgeneration despite explicit instructions. These findings contribute valuable insights to the discourse on language-specific model optimization and establish empirical benchmarks for both multilingual and Portuguese-specialized LLMs in sentiment analysis tasks.
- Open Access
- 31 July 2023
- Published by Brazilian Journals in Revista de Gestão e Secretariado
- Vol. 14 (8) , 13834-13846
Eficiência energética e emissão de poluentes de veículos leves etiquetados pelo PBE veicular
No Brasil, um programa coordenado e regulamentado pelo INMETRO tem como objetivo alertar os consumidores acerca da eficiência energética de bens de consumo e edificações através da Etiqueta Nacional de Conservação de Energia (ENCE), afixada nos produtos de maneira voluntária ou compulsória. O Programa Brasileiro de Etiquetagem Veicular (PBE Veicular), é uma parceria entre o INMETRO e o CONPET visando a prestação de serviço ao público e estímulo a fabricação e a importação de veículos mais eficientes e econômicos. Para tanto, este artigo tem como objetivo explorar as relações das variáveis contínuas poluentes cobertos pelo programa PBE Veicular com o consumo energético de cada categoria de veículo etiquetado em um ano de referência. Como resultado, foi evidenciado a relação positiva entre o dióxido de carbono e o consumo energético veicular, evidenciando a relação entre autonomia e eficiência energética veicular.
- 31 July 2023
- Published by Brazilian Journals in Revista de Gestão e Secretariado
- Vol. 14 (8) , 13834-13846
Open AccessEficiência energética e emissão de poluentes de veículos leves etiquetados pelo PBE veicular
No Brasil, um programa coordenado e regulamentado pelo INMETRO tem como objetivo alertar os consumidores acerca da eficiência energética de bens de consumo e edificações através da Etiqueta Nacional de Conservação de Energia (ENCE), afixada nos produtos de maneira voluntária ou compulsória. O Programa Brasileiro de Etiquetagem Veicular (PBE Veicular), é uma parceria entre o INMETRO e o CONPET visando a prestação de serviço ao público e estímulo a fabricação e a importação de veículos mais eficientes e econômicos. Para tanto, este artigo tem como objetivo explorar as relações das variáveis contínuas poluentes cobertos pelo programa PBE Veicular com o consumo energético de cada categoria de veículo etiquetado em um ano de referência. Como resultado, foi evidenciado a relação positiva entre o dióxido de carbono e o consumo energético veicular, evidenciando a relação entre autonomia e eficiência energética veicular.