FallacyES-Political: A Multiclass Dataset of Fallacies in Spanish Political Debates
Fallacies are pervasive in political discourse, shaping public opinion and influencing decision-making. Automatic detection and classification of fallacies is a challenging task, especially in non-English languages due to limited resources. In this study, we present FallacyES-Political, a novel data...
| Autores: | , , , |
|---|---|
| Tipo de recurso: | artículo |
| Estado: | Versión publicada |
| Fecha de publicación: | 2025 |
| País: | España |
| Institución: | Universidad de Sevilla (US) |
| Repositorio: | idUS. Depósito de Investigación de la Universidad de Sevilla |
| OAI Identifier: | oai:idus.us.es:11441/180727 |
| Acceso en línea: | https://hdl.handle.net/11441/180727 https://doi.org/10.26342/2025-74-9 |
| Access Level: | acceso abierto |
| Palabra clave: | Spanish Linguistic Resources Political Discourse Analysis Fallacy Classification Recursos Linguísticos en Español Análisis del Discurso Político Clasificación de Falacias |
| Sumario: | Fallacies are pervasive in political discourse, shaping public opinion and influencing decision-making. Automatic detection and classification of fallacies is a challenging task, especially in non-English languages due to limited resources. In this study, we present FallacyES-Political, a novel dataset of fallacies extracted from 19 electoral debates held in Spain over three decades. The dataset comprises nearly 2,000 fallacies categorized into 16 types. To evaluate the dataset’s utility, we conducted a comprehensive benchmarking of state-of-the-art Large Language Models (LLMs) in zero-shot classification. The results highlight the complexity of fallacy classification and the limitations of current LLMs in understanding context-dependent argumentation. Furthermore, we demonstrate the advantages of fine-tuning a compact, domain-specific model over relying on general-purpose LLMs, achieving notable improvements in classification accuracy with a more sustainable approach. |
|---|