Outliers in dynamic topic modeling are often discarded as noise, yet some act as early signals of emerging topics. We introduce a temporal taxonomy of news document trajectories that distinguishes anticipatory outliers, documents that appear before a topic forms but later integrate into it, from those that reinforce existing topics or remain isolated. This taxonomy bridges weak-signal detection and dynamic topic modeling, clarifying how individual articles anticipate, initiate, or drift within evolving clusters. We implement it within a cumulative clustering framework using document- embeddings from eleven state-of-the-art language models and apply it retrospectively to HydroNewsFr, a French news corpus on the hydrogen economy curated for this study. Inter-model agreement on anticipatory outliers indicates that a small high-agreement subset yields robust confidence estimates. Complementary qualitative case studies further demonstrate their potential value as early indicators of emerging narratives. All reproducibility materials and results are available at https://anonymous.4open.science/status/lrec_from_noise_to_signal-B721.

Cet article vise à étudier comment le style d’écriture influence la dispersion des plongements vectoriels de divers grands modèles de langage. Alors que les premiers modèles de type transformeur étaient prin- cipalement axés sur la modélisation thématique, cette étude examine le rôle du style d’écriture dans la configuration de l’espace vectoriel. À partir d’un corpus littéraire faisant varier thématiques et styles, nous comparons la sensibilité des modèles de langage en français et en anglais. En analysant ainsi l’impact spécifique du style sur la dispersion vectorielle, nous cherchons à mieux comprendre com- ment les modèles de langage traitent l’information stylistique, contribuant ainsi à leur interprétabilité globale. Ceci est un résumé de l’article “Embedding Style Beyond Topics: Analyzing Dispersion Effects Across Different Language Models” publié dans les actes de la conférence COLING 2025 (Icard et al., 2025) et accessible à l’URL : https://aclanthology.org/2025.coling-main.236/.

This paper analyzes how writing style affects the dispersion of embedding vectors across multiple, state-of-the-art language models. While early transformer models primarily aligned with topic modeling, this study examines the role of writing style in shaping embedding spaces. Using a literary corpus that alternates between topics and styles, we compare the sensitivity of language models across French and English. By analyzing the particular impact of style on embedding dispersion, we aim to better understand how language models process stylistic information, contributing to their overall interpretability.

We present a corpus of 100 documents, named OBSINFOX, selected from 17 sources of French press considered unreliable by expert agencies, annotated using 11 labels by 8 annotators. By collecting more labels than usual, by more annotators than is typically done, we can identify features that humans consider as characteristic of fake news, and compare them to the predictions of automated classifiers. We present a topic and genre analysis using Gate Cloud, indicative of the prevalence of satire-like text in the corpus. We then use the subjectivity analyzer VAGO, and a neural version of it, to clarify the link between ascriptions of the label Subjective and ascriptions of the label Fake News. The annotated dataset is available online at the following url: https://github.com/obs-info/obsinfox Keywords: Fake News, Multi-Labels, Subjectivity, Vagueness, Detail, Opinion, Exaggeration, French Press

This paper investigates the language of propaganda and its stylistic features. It presents the PPN dataset, standing for Propagandist Pseudo-News, a multisource, multilingual, multimodal dataset composed of news articles extracted from websites identified as propaganda sources by expert agencies. A limited sample from this set was randomly mixed with papers from the regular French press, and their URL masked, to conduct an annotation-experiment by humans, using 11 distinct labels. The results show that human annotators were able to reliably discriminate between the two types of press across each of the labels. We use different NLP techniques to identify the cues used by annotators, and to compare them with machine classification: first the analyzer VAGO to detect discourse vagueness and subjectivity, and then four different classifiers, two based on RoBERTa, one CATS using syntax, and one XGBoost combining syntactic and semantic features.

L’outil VAGO est un système expert de détection du vague lexical qui mesure aussi le degré de subjectivité du discours, ainsi que son niveau de détail. Dans cet article, nous construisons un clone neuronal de VAGO, fondé sur une architecture de type BERT, entraîné à partir des scores du VAGO symbolique sur un corpus de presse française (FreSaDa). L’analyse qualitative et quantitative montre la fidélité de la version neuronale. En exploitant des outils d’explicabilité (LIME), nous montrons ensuite l’intérêt de cette version neuronale d’une part pour l’enrichissement des lexiques de la version symbolique, et d’autre part pour la production de versions dans d’autres langues.