TrustedNews is a research project on trustworthy AI for the written press.<\/p>\n\n\n\n
We are group of AI researchers and digital media practitioners working on the analysis of informational quality in press documents.<\/p>\n\n\n\n
Objectives<\/h2>\n\n\n\n
Research questions:<\/strong> How objective or subjective is a press report? How vague or precise is it? Was the document AI generated? Which parts of a document are particularly checkworthy? Can the text be qualified as fake news and on what basis? Is the text driven by a specific agenda, such as propagandist motives, or is the intention to transparently inform?<\/p>\n\n\n\n Methods:<\/strong> We use neuro-symbolic methods to answer these questions, comparing corpora coming from different press groups and sources. We take advantage of the large data bank of the SIPA-Ouest France group, and rely on the expertise of journalists to define analytics with humans in the loop.<\/p>\n\n\n\n Applications<\/strong>: The project is intended for expert as well as lay users. It aims to leverage our analytics for media literacy and content enhancement.<\/p>\n\n\n\n <\/p>\n\n\n\n <\/p>\n\n\n\n Here is a recent article about our project in the CNRS Newsletter:<\/p>\n\n\n\n \u00ab\u00a0IA: d\u00e9tecter le vague pour mieux voir le fake\u00a0\u00bb<\/a><\/p>\n\n\n\n Keep posted, we will seek to recruit an AI engineer or postdoc.<\/p>\n\n\n\n <\/p>\n\n\n\n The project is an Astrid Maturation project (2026-2028), funded by the Agence Innovation Defense and operated by the Agence Nationale de la Recherche. The project is an elaboration of the earlier project Hybrinfox (2022-2024, Institut Nicod\/IRISA\/Mondeca\/Airbus).<\/p>\n\n\n\n <\/p>\n\n\n\n \u00ab\u00a0Reliable News or Propagandist News? A Neurosymbolic Model Using Genre, Topic, and Persuasion Techniques to Improve Robustness in Classification<\/a><\/strong>\u00a0\u00bb Information Disorder Workshop, LREC 2026<\/p>\n\n\n\n \u00ab\u00a0<\/a>Measuring Vagueness-Based Persuasion Techniques in an AI-Generated Influence Campaign<\/a><\/strong>\u00a0\u00bb Infox sur Seine 2026.<\/p>\n\n\n\n \u00ab\u00a0Embedding Style Beyond Topics: Analyzing Dispersion Effects Across Different Language Models<\/a><\/strong>\u00a0\u00bb COLING 2025.<\/p>\n<\/div>\n\n\n\n \u00ab\u00a0HYBRINFOX at CheckThat! 2024 – Task 1: Enhancing Language Models with Structured Information for Check-Worthiness Estimation<\/a><\/strong>\u00a0\u00bb CLEF 2024, CheckThat! Lab<\/p>\n\n\n\n \u00ab\u00a0HYBRINFOX at CheckThat! 2024 – Task 2: Enriching BERT Models with the Expert System VAGO for Subjectivity Detection<\/a><\/strong>\u00a0\u00bb CLEF 2024, CheckThat! Lab (Winner method for English, 1st of 15)<\/p>\n\n\n\n \u00ab\u00a0Exposing Propaganda: an Analysis of Stylistic Cues Comparing Human annotations and machine classification<\/a><\/strong>\u00a0\u00bb EACL 2024, Third Workshop on Understanding Implicit and Underspecified Language<\/em><\/p>\n\n\n\n \u00ab\u00a0A Multilabel Dataset of French Fake News: Human and Machine Insights<\/a><\/strong>\u00a0\u00bb LREC-COLING 2024<\/p>\n\n\n\n \u00ab\u00a0Measuring Vagueness and Subjectivity in Texts: from symbolic to neural VAGO<\/a><\/strong>\u00a0\u00bb 2023 IEEE International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT).<\/p>\n\n\n\n \u00ab\u00a0Un traitement hybride du vague textuel: du syst\u00e8me expert VAGO \u00e0 son clone neuronal<\/a><\/strong>\u00a0\u00bb TALN 2023.<\/p>\n\n\n\n \u00ab\u00a0VAGO: un outil en ligne de mesure du vague et de la subjectivit\u00e9<\/a><\/strong>\u00a0\u00bb Conf\u00e9rence nationale sur les applications pratiques de l’intelligence artificielle<\/em> (APIA 2002).<\/p>\n\n\n\n \u00ab\u00a0Combining Vagueness Detection with Deep-Learning to Identify Fake News<\/a><\/strong>\u00a0\u00bb FUSION 2021, 24th international conference on Information Fusion<\/em>.<\/p>\n\n\n\n propagIA<\/strong><\/a><\/p>\n\n\n\nNews<\/h2>\n\n\n\n
Consortium<\/h2>\n\n\n\n
\n
Context<\/h2>\n\n\n\n
Publications<\/h2>\n\n\n\n
Datasets<\/h2>\n\n\n\n
![\"\"](\"http:\/\/trustednews.fr\/wp-content\/uploads\/2026\/01\/logos_trustednews2-e1768889002520-1024x601.png\")
<\/figure>\n<\/figure>\n<\/div>\n\n\n\n![\"\"](\"https:\/\/trustednews.fr\/wp-content\/uploads\/2026\/01\/AID_ANR-1024x576.png\")
<\/figure>\n","protected":false},"excerpt":{"rendered":"