A Survey on Exploring Real and Virtual Social Network Rumors: State-of-the-Art and Research Challenges

Q He, S Zhang, Y Cai, W Yuan, L Ma, K Yu - ACM Computing Surveys, 2025 - dl.acm.org
This survey reviews the phenomenon of rumor propagation in social networks, defining
rumors and their manifestations, and highlighting the societal confusion, panic, and harm …

How verbal text guides the interpretation of advertisement images: a predictive typology of verbal anchoring

F Bünzli, MJ Eppler - Communication Theory, 2024 - academic.oup.com
One of the key functions of verbal text in modern advertising is to anchor (ie, constrain) the
meaning of the accompanying image, thereby leading the audience toward a preferred …

Verifying Cross-modal Entity Consistency in News using Vision-language Models

S Tahmasebi, E Müller-Budack, R Ewerth - arxiv preprint arxiv …, 2025 - arxiv.org
The web has become a crucial source of information, but it is also used to spread
disinformation, often conveyed through multiple modalities like images and text. The …

Multimodal news discourse and COVID-19: on the interplay between stylistic features and images in three UK newsbrands' early framing of (the pandemic in) Italy

A Riggs - Language and Intercultural Communication, 2024 - Taylor & Francis
This study of UK online news articles about COVID-19 in Italy builds upon prior work by
Filmer and Riggs. Using multimodal analysis including DNVA, I analyse the interplay …

Multimodal meaning making in news communication about immigration: using the NewsScape corpus to explore co-verbal images in TV news

C Hart - Frontiers in Communication, 2024 - frontiersin.org
The communication of news relies on semiotic resources besides language, including
various audiovisual modes of representation. Owing to the difficulties associated with …

Multimodal prosody: gestures and speech in the perception of prominence in Spanish

M Jiménez-Bravo, V Marrero-Aguiar - Frontiers in Communication, 2024 - frontiersin.org
Multimodal communication cannot be properly understood without analyzing the natural
interweaving of speech and gestures as it typically occurs in everyday spoken language …

WikiScenes with Descriptions: Aligning Paragraphs and Sentences with Images in Wikipedia Articles

Ö Alaçam, R Utescher, H Grönner… - Proceedings of the …, 2024 - aclanthology.org
Abstract Research in Language & Vision rarely uses naturally occurring multimodal
documents as Wikipedia articles, since they feature complex image-text relations and …

Multimodal prosody: gestures and speech in the perception of prominence in Spanish

M Jiménez-Bravo Bonilla, V Marreno-Aguiar - 2024 - docta.ucm.es
Multimodal communication cannot be properly understood without analyzing the natural
interweaving of speech and gestures as it typically occurs in everyday spoken language …

Deep learning for news topic identification in limited supervision and unsupervised settings

A Hatefi - 2024 - diva-portal.org
In today's world, following news is crucial for decision-making and staying informed. With the
growing volume of daily news, automated processing is essential for timely insights and in …

A COMPARATIVE STUDY ON IMAGE-TEXT RELATIONS IN BIG PHARMA'SCODES OF ETHICS

C Giglioni, E Patat - Belgrade English Language and …, 2023 - avesis.istanbul.edu.tr
The study of image-text interconnections offers an interdisciplinary approach to understand
and contextualise visuals. The present research explores image-text relations in codes of …