Information Diffusion Prediction Based on User Multi-Dimensional Feature Interaction

Information diffusion prediction, the forecasting of propagation paths, provides critical insights into information spread mechanisms, directly enabling applications like misinformation spread forecasting and detection for malicious account. Prior research primarily focused on combining user social graphs and information cascades for prediction, often overlooking the distinct role characteristics users exhibit during interactions. Classifying users into different roles enables the construction of a multi-layered social graph, facilitating the extraction of deeper user features. This paper introduces a model that leverages multi-dimensional interactions between user features. Specifically, to account for users' dynamic preferences, we construct sequential hypergraphs from information cascades using timestamps and utilize a hypergraph neural network to extract users' dynamic features. Furthermore, to capture users' static features, we build multi-layer social networks from the social graph based on users' roles. We employ graph convolutional networks to separately extract static features from each layer and subsequently fuse them using an attention mechanism. Superior performance of our framework is evidenced by experimental validation on real-world datasets against cutting-edge benchmarks.

• Publication year

  2025

• Venue

  International Conference on Information and Knowledge Management

• Publication date

  2025-11-10

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1145/3746252.3760835
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Enhancing Multi-Scale Diffusion Prediction via Sequential Hypergraphs and Adversarial Learning

  2024cited by this paper
• CasFlow: Exploring Hierarchical Structures and Propagation Uncertainty for Cascade Prediction

  2023cited by this paper
• GRASS: Learning Spatial–Temporal Properties From Chainlike Cascade Data for Microscopic Diffusion Prediction

  2023cited by this paper
• Transformer-enhanced Hawkes process with decoupling training for information cascade prediction

  2022cited by this paper
• Modeling Multi-View Interactions with Contrastive Graph Learning for Collaborative Filtering

  2022cited by this paper
• Improving Information Cascade Modeling by Social Topology and Dual Role User Dependency

  2022cited by this paper
• MS-HGAT: Memory-Enhanced Sequential Hypergraph Attention Network for Information Diffusion Prediction

  2022cited by this paper
• Decoupling Representation and Regressor for Long-Tailed Information Cascade Prediction

  2021cited by this paper
• Neural Diffusion Model for Microscopic Cascade Study

  2021cited by this paper
• A Survey of Information Cascade Analysis: Models, Predictions, and Recent Advances

  2021cited by this paper
• Full-Scale Information Diffusion Prediction With Reinforced Recurrent Networks

  2021cited by this paper
• DyHGCN: A Dynamic Heterogeneous Graph Convolutional Network to Learn Users' Dynamic Preferences for Information Diffusion Prediction

  2020cited by this paper
• Inf-VAE: A Variational Autoencoder Framework to Integrate Homophily and Influence in Diffusion Prediction

  2020cited by this paper
• Multi-scale Information Diffusion Prediction with Reinforced Recurrent Networks

  2019cited by this paper
• A Sequential Neural Information Diffusion Model with Structure Attention

  2018cited by this paper
• Topological Recurrent Neural Network for Diffusion Prediction

  2017cited by this paper
• RolX: structural role extraction & mining in large graphs

  2012cited by this paper

• No citing papers are available for this paper.