Date of Award

5-12-2025

Document Type

Thesis

Degree Name

Master of Science (MS)

Department

Computer Science

First Advisor

Nitin Agarwal

Abstract

Over the past decade, social media platforms have rapidly evolved in scale, functionality, and user engagement, encouraging individuals to maintain active presences across multiple networks. This complex, interconnected ecosystem has also enabled information actors to exploit cross-platform dynamics to amplify the reach of their content and strategically target diverse audiences. Recognizing the persistence and adaptability of such actors, this research emphasizes the need for robust models that can effectively capture and analyze cross-platform narrative diffusion. To this end, we propose a framework that utilizes temporal knowledge graphs to model the evolution and relationships among narratives across platforms. We extract temporal communities that represent macro-narratives and apply sequential pattern mining techniques to identify recurrent narrative propagation strategies—referred to as narrative templates. These templates reveal the behavioral patterns that various actors adopt when disseminating content across different social media platforms. The proposed approach is validated through an empirical analysis of 4,817 Instagram posts, 2,560 TikTok posts, 11,134 posts from X (formerly Twitter), and 7,327 YouTube videos. Our findings demonstrate the model’s effectiveness in uncovering narrative templates associated with Pro-Taiwan and Pro-China actors within the Asia-Pacific political context. We identify and compare two broad categories of narrative templates based on their support and confidence metrics, shedding light on the distinct dissemination strategies employed by opposing information campaigns.

Download

Share

COinS