A Social Dynamical System for Twitter Analysis

2025-03-25

AI Summary

This work addresses the problem of modeling and predicting latent opinion dynamics among users in social media. We propose the Latent Social Dynamical System (LSDS), a unified, differentiable graph neural ODE framework that generalizes classical opinion dynamics models. LSDS introduces a text-driven latent state encoder to disentangle surface-level expressions from underlying beliefs. It supports modular plug-and-play integration of dynamical models, encoders, and downstream tasks—e.g., interaction prediction. By synergistically combining graph neural networks (GNNs), neural ODEs (specifically GraphODE), and dynamic graph modeling, LSDS achieves significant performance gains on a newly curated Twitter temporal dataset. The framework is highly generalizable, modular, and interpretable. To foster reproducibility and further research, we will open-source both the code and the dataset.

Technology Category

• Natural Language Processing: Sentence-level Semantics, Textual Inference, etc.
• Machine Learning: Large Multimodal Models (LMMs)
• Application Domains: Humanities & Computational Social Science

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• User Modeling, Personalization and Recommendation: Social recommender systems and personalization for the social Web

Abstract

Understanding the evolution of public opinion is crucial for informed decision-making in various domains, particularly public affairs. The rapid growth of social networks, such as Twitter (now rebranded as X), provides an unprecedented opportunity to analyze public opinion at scale without relying on traditional surveys. With the rise of deep learning, Graph Neural Networks (GNNs) have shown great promise in modeling online opinion dynamics. Notably, classical opinion dynamics models, such as DeGroot, can be reformulated within a GNN framework. We introduce Latent Social Dynamical System (LSDS), a novel framework for modeling the latent dynamics of social media users' opinions based on textual content. Since expressed opinions may not fully reflect underlying beliefs, LSDS first encodes post content into latent representations. It then leverages a GraphODE framework, using a GNN-based ODE function to predict future opinions. A decoder subsequently utilizes these predicted latent opinions to perform downstream tasks, such as interaction prediction, which serve as benchmarks for model evaluation. Our framework is highly flexible, supporting various opinion dynamic models as ODE functions, provided they can be adapted into a GNN-based form. It also accommodates different encoder architectures and is compatible with diverse downstream tasks. To validate our approach, we constructed dynamic datasets from Twitter data. Experimental results demonstrate the effectiveness of LSDS, highlighting its potential for future applications. We plan to publicly release our dataset and code upon the publication of this paper.

Problem

• Model latent opinion dynamics from Twitter content
• Predict future opinions using GraphODE and GNNs
• Enable flexible integration of various dynamic models

Innovation

• Latent Social Dynamical System for opinion modeling
• GraphODE framework with GNN-based ODE function
• Flexible support for various dynamic models