Year: 2025
Type: conference-paper
Abstract: Current Portuguese Automated Fact-Checking (AFC) research often relies on datasets lacking integrated external evidence crucial for comprehensive verification.This study addresses this gap by systematically enriching Portuguese misinformation datasets.We retrieve web evidence by simulating user information-seeking behavior, guided by core claims extracted using Large Language Models (LLMs).Additionally, we apply a semi-automated validation framework to enhance dataset reliability.Our analysis reveals that inherent dataset characteristics impact data properties, evidence retrieval, and AFC model performance.While enrichment generally improves detection, its efficacy varies, influenced by challenges such as self-reinforcing online misinformation and API limitations.
Authors: Juliana Gomes, Eduardo Garcia, Arlindo Rodrigues Galvão Filho
Institution: Universidade Federal de Goiás
Language: English
Subfield: Sociology and Political Science
Field: Social Sciences
Domain: Social Sciences
Open Access status: gold
Award: G6800455736
OpenAlex ID: W4412889037