🤖 AI Summary
This study investigates how cultural background and discussion topics jointly shape the affective structure of signed ego-centered networks (i.e., social ties annotated with positive/negative sentiment) on Twitter. Leveraging 26 large-scale, cross-cultural, multi-topic empirical datasets, we integrate signed network modeling, fine-grained sentiment annotation, and rigorous statistical testing. Our findings are: (1) Cultural effects operate independently of topic and remain robust even when topic is controlled; (2) Polarizing topics significantly amplify cross-cultural disparities in negative sentiment; (3) Negative sentiment persists stably across all ego-network layers—contradicting the conventional assumption of its decay with network distance; (4) Topic breadth reliably predicts the overall positivity of relational ties. This work provides the first empirical demonstration of separable, joint cultural–topical effects on affective networks, establishing a novel theoretical framework and interpretable predictive metrics for cross-cultural social media sentiment analysis.
📝 Abstract
Humans are known to structure social relationships according to certain patterns, such as the Ego Network Model (ENM). These patterns result from our innate cognitive limits and can therefore be observed in the vast majority of large human social groups. Until recently, the main focus of research was the structural characteristics of this model. The main aim of this paper is to complement previous findings with systematic and data-driven analyses on the positive and negative sentiments of social relationships, across different cultures, communities and topics of discussion. A total of 26 datasets were collected for this work. It was found that contrary to previous findings, the influence of culture is not easily ``overwhelmed'' by that of the topic of discussion. However, more specific and polarising topics do lead to noticeable increases in negativity across all cultures. These negativities also appear to be stable across the different levels of the ENM, which contradicts previous hypotheses. Finally, the number of generic topics being discussed between users seems to be a good predictor of the overall positivity of their relationships.