Cross-Platform Narrative Prediction: Leveraging Platform-Invariant Discourse Networks

2025-10-10

AI Summary

This work addresses the fragility of existing cross-platform information propagation prediction methods, which overly rely on shared URLs, hashtags, or user tracking—signals vulnerable to obfuscation or platform-specific constraints. We propose a platform-agnostic discourse network modeling framework that captures narrative-level user engagement across heterogeneous platforms (X, TikTok, Truth Social, Telegram). By constructing a discourse-coherence-driven cross-platform discourse network, we recast propagation prediction as a network proximity measurement problem. Crucially, our approach requires no cross-platform user alignment or explicit inter-platform linking, relying solely on structural alignment of narrative content. Evaluated on 5.7 million real-world posts, it achieves >94% AUC and enables early detection—hours to days in advance—of election-related crisis rumors. Results demonstrate that reliable inference can be achieved with only a small cohort of active users, underscoring its practical utility for real-time early warning and targeted intervention.

Technology Category

• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Application Domains: Misinformation & Fake News
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Social Networks and Social Media: Influence propagation, information diffusion, and the prediction on networks
• Responsible Web: Mitigating misinformation and disinformation
• Web Mining and Content Analysis: Content-based information diffusion

Abstract

Online narratives spread unevenly across platforms, with content emerging on one site often appearing on others, hours, days or weeks later. Existing cross-platform information diffusion models often treat platforms as isolated systems, disregarding cross-platform activity that might make these patterns more predictable. In this work, we frame cross-platform prediction as a network proximity problem: rather than tracking individual users across platforms or relying on brittle signals like shared URLs or hashtags, we construct platform-invariant discourse networks that link users through shared narrative engagement. We show that cross-platform neighbor proximity provides a strong predictive signal: adoption patterns follow discourse network structure even without direct cross-platform influence. Our highly-scalable approach substantially outperforms diffusion models and other baselines while requiring less than 3% of active users to make predictions. We also validate our framework through retrospective deployment. We sequentially process a datastream of 5.7M social media posts occurred during the 2024 U.S. election, to simulate real-time collection from four platforms (X, TikTok, Truth Social, and Telegram): our framework successfully identified emerging narratives, including crises-related rumors, yielding over 94% AUC with sufficient lead time to support proactive intervention.

Problem

• Predicting narrative spread across platforms using network proximity
• Modeling cross-platform information diffusion without isolated assumptions
• Identifying emerging narratives through platform-invariant discourse networks

Innovation

• Constructs platform-invariant discourse networks for prediction
• Uses cross-platform neighbor proximity as predictive signal
• Processes datastreams sequentially to simulate real-time collection