An Integrated Approach for Political Bias Prediction and Explanation Based on Discursive Structure - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

An Integrated Approach for Political Bias Prediction and Explanation Based on Discursive Structure

Résumé

One crucial aspect of democracy is fair information sharing. While it is hard to prevent biases in news, they should be identified for better transparency. We propose an approach to automatically characterize biases that takes into account structural differences and that is efficient for long texts. This yields new ways to provide explanations for a textual classifier, going beyond mere lexical cues. We show that: (i) the use of discourse-based structure-aware document representations compare well to local, computationally heavy, or domain-specific models on classification tasks that deal with textual bias (ii) our approach based on different levels of granularity allows for the generation of better explanations of model decisions, both at the lexical and structural level, while addressing the challenge posed by long texts.
Fichier principal
Vignette du fichier
2023.findings-acl.711.pdf (420.92 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-04249724 , version 1 (19-10-2023)

Licence

Paternité

Identifiants

Citer

Nicolas Devatine, Philippe Muller, Chloé Braud. An Integrated Approach for Political Bias Prediction and Explanation Based on Discursive Structure. Findings of the Association for Computational Linguistics (EACL 2023), Jul 2023, Toronto, Canada. pp.11196-11211, ⟨10.18653/v1/2023.findings-acl.711⟩. ⟨hal-04249724⟩
45 Consultations
36 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More