Ridwan Amure

Narratives on social media emerge through the interaction of content, users, and platform-specific structures, yet identifying cohesive narrative formations across platforms remains challenging. This paper introduces Weighted Contextual Focal Structures Analysis (W–CFSA), a graph-based method for discovering structurally embedded narrative groups in multiplex networks. We construct a three-layer multiplex network integrating user–user interactions, user–narrative associations, and narrative–narrative similarity, with edge weights derived from semantic alignment. The method is evaluated on over 70,000 cross-platform data collected from YouTube, TikTok, X (formerly Twitter), and Instagram between January and May 2025, comprising posts related to U.S.-China trade and tariff policies. Empirical results show that W–CFSA identifies focal sets with higher internal cohesion, greater internal density, and more substantial impact on global clustering than a size-matched eigenvector-centrality baseline. Qualitative analysis further indicates that the recovered focal sets correspond to distinct narrative architectures rather than simple stance groupings, demonstrating the value of integrating narrative context with network structure for cross-platform analysis.

We propose a semi-supervised approach that finds anomalous YouTube channels by combining co-commenter networks and engagement features. Our method, named SEPS (Semi-Supervised Embedding-based Propagation Scoring), uses a small set of labeled anomalies to guide the learning process. It trains a graph neural network to embed nodes, spreads those partial labels through a simple classification head, and flags channels that appear suspicious. The model was tested on real data from the Indo-Pacific region which spans 97 channels, 702,160 videos, 12.5 million commenters, and 123.9 million comments. Further tests on synthetic data show that SEPS outperforms older methods in recall, precision, and F1-score. It detects more unlabeled anomalies with fewer false alarms. We also show that it remains effective when only a handful of known anomalies are present, and it can maintain high cluster purity under these conditions. In addition, we discuss how the model can scale to larger datasets and adapt to changes in user behavior. This work contributes a robust way to spot suspicious channels in real-world environments where full labels are scarce.

Over the past decade, online social media has grown in size, features, and complexity, providing users with increased satisfaction and prompting many to maintain accounts across multiple platforms. Information actors have also taken advantage of this environment, using cross-platform dynamics to amplify content’s reach and target specific audiences strategically. As these actors will likely continue exploiting social media, we argue that it is crucial to model cross-platform narratives effectively and identify the patterns-or templates defined in this research-they use to propagate different narratives. To address these challenges, we leverage temporal knowledge graphs to model the relationships between cross-platform narratives, extract temporal communities representing macro-narratives, and apply sequential mining to uncover various narrative templates. These templates reveal the patterns various actors use to spread different narratives across various social media platforms. An analysis of 4,817 Instagram posts, 2,560 TikTok posts, 11,134 X posts, and 7,327 YouTube posts, demonstrates the efficacy of this approach in identifying the templates preferred by Pro-Taiwan and Pro-China actors in the Asia–Pacific political landscape. We identified two groups of narrative templates based on confidence and support. Our further analysis uncovers which templates were favored by Pro-Taiwan and Pro-China supporters.