This paper presents the results of a study on multimodal speaker behaviour in a corpus of online Zoom meetings. We investigate two questions: i) whether speakers display a higher degree of head movement when they exchange verbal feedback than when they don’t, as would be expected if verbal and gestural feedback reinforce one other, and ii) whether they move more or less similarly under the same conditions. Several linear mixed models were fitted to test the difference in head movement values in target and control intervals of two different durations. The results indicate that speakers indeed entrain by moving their heads more in target intervals where verbal feedback is present. This result confirms our expectations. However, speakers also appear to move in less similar ways in the same target intervals. This dissimilarity can be explained by the fact that not all speakers give the same type of gestural feedback, but also by noise created by non-communicative movements in which speakers adjust their positions or reach out for objects during the meeting.

Recognizing disinformation is a challenging task for humans and AI systems. News can be false, misleading, or harmful, and its interpretation often depends on the cultural context of the audience. However, existing datasets rarely account for these contextual and cultural differences, as they are typically not designed from the perspective of news consumers. To address this gap, in this paper, we present the Information Disorder (InDor) corpus, a multilingual dataset of news articles in English, Farsi, Italian, and Russian, annotated for information disorder detection and explanation. The corpus was developed through a participatory process involving contributors from diverse cultural and professional backgrounds, who engaged in data collection, annotation, and evaluation of Large Language Model (LLM) performance on the task. Our findings highlight that false and manipulated news manifest differently across cultural settings, and that current LLMs fail to adequately capture this complexity. This underscores the need for culturally aware computational approaches in the study of information disorder.