Detalle Publicación

Semantic similarity models for automated fact-checking: ClaimCheck as a claim matching tool

Autores: Larraz Elorriaga, Irene (Autor de correspondencia); Miguez, R.; Sallicati, F.
Título de la revista: PROFESIONAL DE LA INFORMACION
ISSN: 1386-6710
Volumen: 32
Número: 3
Páginas: e320321
Fecha de publicación: 2023
Resumen:
This article presents the experimental design of ClaimCheck, an artificial intelligence tool for detecting repeated falsehoods in political discourse using a semantic similarity model developed by the fact-checking organization Newtral in collaboration with ABC Australia. The study reviews the state of the art in algorithmic fact-checking and proposes a definition of claim matching. Additionally, it outlines the scheme for annotating similar sentences and presents the results of experiments conducted with the tool.
Impacto: