@inproceedings{faye-etal-2026-reliable,
title = "Reliable News or Propagandist News? A Neurosymbolic Model Using Genre, Topic, and Persuasion Techniques to Improve Robustness in Classification",
author = "Faye, G{\'e}raud and
Icard, Benjamin and
Casanova, Morgane and
Gadek, Guillaume and
Gravier, Guillaume and
Ouerdane, Wassila and
Hudelot, Celine and
Gatepaille, Sylvain and
{\'E}gr{\'e}, Paul",
editor = "Frenda, Simona and
Stranisci, Marco Antonio and
Ashraf, Shaina and
Ren, Ada and
Konstas, Ioannis and
Naseem, Usman",
booktitle = "Proceedings of the 1st Workshop on Information Disorder ({I}n{D}or) @ {LREC} 2026",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.indor-1.6/",
doi = "10.63317/2nn33a2we7xp",
pages = "55--65",
ISBN = "978-2-493814-87-6",
abstract = "Among news disorders, propagandist news are particularly insidious, because they tend to mix oriented messages with factual reports intended to look like reliable news. To detect propaganda, extant approaches based on Language Models such as BERT are promising but often overfit their training datasets, due to biases in data collection. To enhance classification robustness and improve generalization to new sources, we propose a neurosymbolic approach combining non-contextual text embeddings (fastText) with symbolic conceptual features such as genre, topic, and persuasion techniques. Results show improvements over equivalent text-only methods, and ablation studies as well as explainability analyses confirm the benefits of the added features. Keywords: Information disorder, Fake news, Propaganda, Classification, Topic modeling, Hybrid method, Neurosymbolic model, Ablation, Robustness"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="faye-etal-2026-reliable">
<titleInfo>
<title>Reliable News or Propagandist News? A Neurosymbolic Model Using Genre, Topic, and Persuasion Techniques to Improve Robustness in Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Géraud</namePart>
<namePart type="family">Faye</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benjamin</namePart>
<namePart type="family">Icard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Morgane</namePart>
<namePart type="family">Casanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guillaume</namePart>
<namePart type="family">Gadek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guillaume</namePart>
<namePart type="family">Gravier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wassila</namePart>
<namePart type="family">Ouerdane</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Celine</namePart>
<namePart type="family">Hudelot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sylvain</namePart>
<namePart type="family">Gatepaille</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Égré</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Workshop on Information Disorder (InDor) @ LREC 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Simona</namePart>
<namePart type="family">Frenda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="given">Antonio</namePart>
<namePart type="family">Stranisci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shaina</namePart>
<namePart type="family">Ashraf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ada</namePart>
<namePart type="family">Ren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ioannis</namePart>
<namePart type="family">Konstas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Usman</namePart>
<namePart type="family">Naseem</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">978-2-493814-87-6</identifier>
</relatedItem>
<abstract>Among news disorders, propagandist news are particularly insidious, because they tend to mix oriented messages with factual reports intended to look like reliable news. To detect propaganda, extant approaches based on Language Models such as BERT are promising but often overfit their training datasets, due to biases in data collection. To enhance classification robustness and improve generalization to new sources, we propose a neurosymbolic approach combining non-contextual text embeddings (fastText) with symbolic conceptual features such as genre, topic, and persuasion techniques. Results show improvements over equivalent text-only methods, and ablation studies as well as explainability analyses confirm the benefits of the added features. Keywords: Information disorder, Fake news, Propaganda, Classification, Topic modeling, Hybrid method, Neurosymbolic model, Ablation, Robustness</abstract>
<identifier type="citekey">faye-etal-2026-reliable</identifier>
<identifier type="doi">10.63317/2nn33a2we7xp</identifier>
<location>
<url>https://aclanthology.org/2026.indor-1.6/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>55</start>
<end>65</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Reliable News or Propagandist News? A Neurosymbolic Model Using Genre, Topic, and Persuasion Techniques to Improve Robustness in Classification
%A Faye, Géraud
%A Icard, Benjamin
%A Casanova, Morgane
%A Gadek, Guillaume
%A Gravier, Guillaume
%A Ouerdane, Wassila
%A Hudelot, Celine
%A Gatepaille, Sylvain
%A Égré, Paul
%Y Frenda, Simona
%Y Stranisci, Marco Antonio
%Y Ashraf, Shaina
%Y Ren, Ada
%Y Konstas, Ioannis
%Y Naseem, Usman
%S Proceedings of the 1st Workshop on Information Disorder (InDor) @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma de Mallorca, Spain
%@ 978-2-493814-87-6
%F faye-etal-2026-reliable
%X Among news disorders, propagandist news are particularly insidious, because they tend to mix oriented messages with factual reports intended to look like reliable news. To detect propaganda, extant approaches based on Language Models such as BERT are promising but often overfit their training datasets, due to biases in data collection. To enhance classification robustness and improve generalization to new sources, we propose a neurosymbolic approach combining non-contextual text embeddings (fastText) with symbolic conceptual features such as genre, topic, and persuasion techniques. Results show improvements over equivalent text-only methods, and ablation studies as well as explainability analyses confirm the benefits of the added features. Keywords: Information disorder, Fake news, Propaganda, Classification, Topic modeling, Hybrid method, Neurosymbolic model, Ablation, Robustness
%R 10.63317/2nn33a2we7xp
%U https://aclanthology.org/2026.indor-1.6/
%U https://doi.org/10.63317/2nn33a2we7xp
%P 55-65
Markdown (Informal)
[Reliable News or Propagandist News? A Neurosymbolic Model Using Genre, Topic, and Persuasion Techniques to Improve Robustness in Classification](https://aclanthology.org/2026.indor-1.6/) (Faye et al., InDor 2026)
ACL
- Géraud Faye, Benjamin Icard, Morgane Casanova, Guillaume Gadek, Guillaume Gravier, Wassila Ouerdane, Celine Hudelot, Sylvain Gatepaille, and Paul Égré. 2026. Reliable News or Propagandist News? A Neurosymbolic Model Using Genre, Topic, and Persuasion Techniques to Improve Robustness in Classification. In Proceedings of the 1st Workshop on Information Disorder (InDor) @ LREC 2026, pages 55–65, Palma de Mallorca, Spain. ELRA Language Resources Association (ELRA).