Comparing Explainable AI Techniques In Language Models: A Case Study For Fake News Detection in Portuguese

Journal of the Brazilian Computer Society 2026 Open access

Read full text
Authors: Jéssica [UNESP} [UNESP] Vicentini, Rafael Bezerra de Menezes Rodrigues, Arnaldo Candido Junior, Ivan Rizzo Guilherme
DOI: 10.5753/jbcs.2026.5787
Cited by: 1
References: 13

Abstract

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.

Fields of Study & Subjects

Misinformation and Its Impacts Explainable Artificial Intelligence (XAI) Big Data and Digital Economy

Publication details

Journal / source
Journal of the Brazilian Computer Society
Publisher
Sociedade Brasileira de Computação
Volume
32
Issue
1
Pages
01–12
Publication date
21 January 2026