PopSim: Social Network Simulation for Social Media Popularity Prediction

TL;DR

PopSim introduces a simulation-based approach using large language models to better capture the dynamic propagation of user-generated content for improved social media popularity prediction.

Contribution

It proposes a novel simulation paradigm with a social-mean-field agent interaction mechanism and multimodal information fusion for more accurate popularity prediction.

Findings

Outperforms state-of-the-art methods with 8.82% lower prediction error

Demonstrates effectiveness of simulation-based modeling for UGC propagation

Provides a new perspective for social media popularity prediction research

Abstract

Accurately predicting the popularity of user-generated content (UGC) is essential for advancing social media analytics and recommendation systems. Existing approaches typically follow an inductive paradigm, where researchers train static models on historical data for popularity prediction. However, the UGC propagation is inherently a dynamic process, and static modeling based on historical features fails to capture the complex interactions and nonlinear evolution. In this paper, we propose PopSim, a novel simulation-based paradigm for social media popularity prediction (SMPP). Unlike the inductive paradigm, PopSim leverages the large language models (LLMs)-based multi-agent social network sandbox to simulate UGC propagation dynamics for popularity prediction. Specifically, to effectively model the UGC propagation process in the network, we design a social-mean-field-based agent interaction mechanism, which models the dual-channel and bidirectional individual-population interactions, enhancing agents' global perception and decision-making capabilities. In addition, we propose a multi-source information aggregation module that transforms heterogeneous social metadata into a uniform formulation for LLMs. Finally, propagation dynamics with multimodal information are fused to provide comprehensive popularity prediction. Extensive experiments on real-world datasets demonstrate that SimPop consistently outperforms the state-of-the-art methods, reducing prediction error by an average of 8.82%, offering a new perspective for research on the SMPP task.