{"slug": "framing-by-wording-framing-by-selection-a-large-scale-two-dimensional-audit-of", "title": "Framing by Wording, Framing by Selection: A Large-Scale Two-Dimensional Audit of French News Headlines, 2022-2025", "summary": "A two-dimensional framework separating salience framing from selection framing was applied to 902,111 deduplicated French news headlines from 25 outlets spanning 2022-2025, according to an arXiv paper (2609.28487v1). The study built a 10,000-headline French supervision set using three LLM annotators with majority-vote resolution and human arbitration, validated against two annotator-independent blind human studies. The authors report that salience and selection divergence are positively correlated yet leave nearly half of outlet-level variance unexplained, that default classification thresholds systematically inflate corpus-level salience estimates, and that headlines mentioning Jews, the Far-right, and Muslims carry the highest detected salience rates; the supervision set, lexicons, and analysis code are released.", "body_md": "arXiv:2609.28487v1 Announce Type: new \nAbstract: News headlines frame public issues both by what they select and by how they word it, yet computational framing work typically collapses these operations into a single score. We introduce a two-dimensional framework that separates salience framing, measured through four wording devices (loaded vocabulary, blame attribution, threat framing, rhetorical question), from selection framing, measured through outlet-level story-form and high-charge distributions. We build a 10,000-headline French supervision set using three LLM annotators with majority-vote resolution and human arbitration, validate the labels against two annotator-independent blind human studies, and apply the strongest classifier to 902,111 deduplicated headlines from 25 French outlets (2022-2025). Three main findings emerge. First, salience and selection divergence are positively correlated yet leave nearly half of outlet-level variance unexplained, populating interpretively distinct off-diagonal cells in a four-cell outlet typology. Second, default classification thresholds systematically inflate corpus-level salience estimates; a precision-floor recalibration protocol corrects this distortion. Third, group-mention analysis reveals sharply unequal salience contexts: headlines mentioning Jews, the Far-right, and Muslims carry the highest detected salience rates, which broad event-context composition does not fully explain (residuals are descriptive, not same-event causal estimates; per-group lexicon precision is reported alongside). To our knowledge, this is the largest framing-focused French headline audit to date; we release the supervision set, lexicons, and analysis code.", "url": "https://wpnews.pro/news/framing-by-wording-framing-by-selection-a-large-scale-two-dimensional-audit-of", "canonical_source": "https://arxiv.org/abs/2609.28487", "published_at": "2026-09-25 04:00:00+00:00", "updated_at": "2026-09-25 04:00:39.894922+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "natural-language-processing", "ai-research"], "entities": ["arXiv", "French news outlets"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/framing-by-wording-framing-by-selection-a-large-scale-two-dimensional-audit-of", "markdown": "https://wpnews.pro/news/framing-by-wording-framing-by-selection-a-large-scale-two-dimensional-audit-of.md", "text": "https://wpnews.pro/news/framing-by-wording-framing-by-selection-a-large-scale-two-dimensional-audit-of.txt", "jsonld": "https://wpnews.pro/news/framing-by-wording-framing-by-selection-a-large-scale-two-dimensional-audit-of.jsonld"}}