Accès ouvert
2026
preprint
OpenAlex
Tarek Mahmoud1, Veronika Solopova, Premtim Sahitaj, Ariana Sahitaj et autres
Temporal language does more than place events on a timeline. In news discourse, references to the past, present, and future can function as rhetorical devices that shape interpretation and persuasion. Here, we study temporal framing, defined as the persuasive use of time-related …
Accès ouvert
2026
preprint
OpenAlex
Tarek Mahmoud1, Veronika Solopova, Premtim Sahitaj, Ariana Sahitaj et autres
Temporal language does more than place events on a timeline. In news discourse, references to the past, present, and future can function as rhetorical devices that shape interpretation and persuasion. Here, we study temporal framing, defined as the persuasive use of time-related …
de, us
(code pays fourni par la source)
Accès ouvert
2026
preprint
OpenAlex
Lukas Stähelin, Veronika Solopova, Max Upravitelev, David Kaplan et autres
Propaganda detection in social media is challenging due to noisy, short texts and low annotation agreements. We introduce a new intent-focused taxonomy of propaganda techniques and compare it against an established, higher-agreement schema. Along three dimensions (model portfolio, schema effects, and prompting …
Accès ouvert
2026
preprint
OpenAlex
Lukas Stähelin, Veronika Solopova, Max Upravitelev, David Kaplan et autres
Propaganda detection in social media is challenging due to noisy, short texts and low annotation agreements. We introduce a new intent-focused taxonomy of propaganda techniques and compare it against an established, higher-agreement schema. Along three dimensions (model portfolio, schema effects, and prompting …
de
(code pays fourni par la source)
Accès ouvert
2026
preprint
OpenAlex
Premtim Sahitaj, Jawan Kolanowski, Ariana Sahitaj, Veronika Solopova et autres
Fact-checking articles encode rich supporting evidence and reasoning, yet this evidence remains largely inaccessible to automated verification systems due to unstructured presentation. We introduce PrimeFacts, a methodology and resource for extracting fine-grained evidence from full fact-checking articles. We compile 13,106 PolitiFact articles …
Accès ouvert
2026
conference-paper
OpenAlex
Vera Schmitt, Niklas Kruse, Premtim Sahitaj, Julius Schöning
Art. 50 II of the EU Artificial Intelligence Act mandates dual transparency for AI-generated content: outputs must be labeled in both human-understandable and machine-readable form for automated verification.This requirement, entering into force in August 2026, collides with fundamental constraints of current generative …
de
(code pays fourni par la source)
Accès ouvert
2026
conference-paper
OpenAlex
Max Upravitelev, Veronika Solopova, Charlott Jakob, Premtim Sahitaj et autres
Detecting climate disinformation narratives typically relies on fixed taxonomies, which do not accommodate emerging narratives.Thus, we re-frame narrative detection as a retrieval task: given a narrative's core message as a query, rank texts from a corpus by alignment with that narrative.This formulation …
de
(code pays fourni par la source)
Accès ouvert
2026
conference-paper
OpenAlex
Premtim Sahitaj, Jawan Kolanowski, Ariana Sahitaj, Veronika Solopova et autres
Fact-checking articles encode rich supporting evidence and reasoning, yet this evidence remains largely inaccessible to automated verification systems due to unstructured presentation. We introduce PrimeFacts, a methodology and resource for extracting fine-grained evidence from full fact-checking articles. We compile 13,106 PolitiFact articles …
Accès ouvert
2026
preprint
OpenAlex
Vera Schmitt, Niklas Kruse, Premtim Sahitaj, Julius Schöning
Art. 50 II of the EU Artificial Intelligence Act mandates dual transparency for AI-generated content: outputs must be labeled in both human-understandable and machine-readable form for automated verification. This requirement, entering into force in August 2026, collides with fundamental constraints of current …
Accès ouvert
2026
preprint
OpenAlex
Max Upravitelev, Veronika Solopova, Charlott Jakob, Premtim Sahitaj et autres
Detecting climate disinformation narratives typically relies on fixed taxonomies, which do not accommodate emerging narratives. Thus, we re-frame narrative detection as a retrieval task: given a narrative's core message as a query, rank texts from a corpus by alignment with that narrative. …
Accès ouvert
2026
preprint
OpenAlex
Max Upravitelev, Veronika Solopova, Jing Yang, Charlott Jakob et autres
Predicting narrative similarity can be understood as an inherently interpretive task: different, equally valid readings of the same text can produce divergent interpretations and thus different similarity judgments, posing a fundamental challenge for semantic evaluation benchmarks that encode a single ground truth. …
Accès ouvert
2026
preprint
OpenAlex
Max Upravitelev, Veronika Solopova, Jing Yang, Charlott Jakob et autres
Predicting narrative similarity can be understood as an inherently interpretive task: different, equally valid readings of the same text can produce divergent interpretations and thus different similarity judgments, posing a fundamental challenge for semantic evaluation benchmarks that encode a single ground truth. …
de
(code pays fourni par la source)