Jéssica Vicentini
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Jéssica Vicentini has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Arnaldo Candido Junior
Universidade Estadual Paulista
1 shared publication - Ivan Rizzo Guilherme
São Paulo State University, UNESP, Brazil
1 shared publication - Rafael Bezerra de Menezes Rodrigues
UNESP - São Paulo State University, School of Technology and Sciences
1 shared publication
Latest Publications
- Open Access
- 20 January 2026
- Published by Sociedade Brasileira de Computação in Journal of the Brazilian Computer Society
- Vol. 32 (1) , 01-12
Comparing Explainable AI Techniques In Language Models: A Case Study For Fake News Detection in Portuguese
Language models are widely used in natural language processing, but their complexity makes interpretation difficult, limiting their adoption in critical decision-making. This work explores Explainable Artificial Intelligence (XAI) techniques, such as LIME and Integrated Gradients (IG), to understand these models. The study evaluates the effectiveness of BERTimbau in classifying Portuguese news as true or fake, using the FakeRecogna and Fake.Br Corpus datasets. In the experiments, LIME proved to be easier to interpret than IG, and both methods showed limitations when applied to texts, as they focus only on the morphological and lexical levels, ignoring other important levels.
- 20 January 2026
- Published by Sociedade Brasileira de Computação in Journal of the Brazilian Computer Society
- Vol. 32 (1) , 01-12
Open AccessComparing Explainable AI Techniques In Language Models: A Case Study For Fake News Detection in Portuguese
Language models are widely used in natural language processing, but their complexity makes interpretation difficult, limiting their adoption in critical decision-making. This work explores Explainable Artificial Intelligence (XAI) techniques, such as LIME and Integrated Gradients (IG), to understand these models. The study evaluates the effectiveness of BERTimbau in classifying Portuguese news as true or fake, using the FakeRecogna and Fake.Br Corpus datasets. In the experiments, LIME proved to be easier to interpret than IG, and both methods showed limitations when applied to texts, as they focus only on the morphological and lexical levels, ignoring other important levels.