Research map / Graph learning / Knowledge and temporal graphs
Mining Unfollow Behavior in Large-Scale Online Social Networks via Spatial-Temporal Interaction
Haozhe Wu, Zhiyuan Hu, Jia Jia, Yaohua Bu, Xiangnan He, Tat-Seng Chua
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Fuse spatial and temporal features with nonlinear interaction modeling instead of handcrafted features | UMHI · Weibo unfollow prediction | Precision: 7.42% | Improved |
| Fuse spatial and temporal features with nonlinear interaction modeling instead of handcrafted features | UMHI · Weibo unfollow prediction | Precision: 6.86% | Improved |
| Add matrix-factorized unfollow history features (ablation) | LINE1 + LINE2 + HAN · Weibo unfollow prediction | Precision: 0.7034 -> 0.7868 | Improved |
| Add matrix-factorized unfollow history features (ablation) | LINE1 + LINE2 + HAN · Weibo unfollow prediction | AUC: 0.7718 -> 0.8673 | Improved |
| Use LINE local structure embeddings rather than global random-walk embeddings | Unfollow prediction models · Weibo unfollow prediction | Precision: 1.73% | Improved |
| Use second-order rather than first-order LINE proximity (ablation) | LINE · Weibo unfollow prediction | Precision: 0.6316 -> 0.6413 | Improved |
| Add LINE second-order proximity to LINE first-order proximity (ablation) | LINE1 · Weibo unfollow prediction | Precision: 0.6316 -> 0.6458 | Improved |
| Use unfollow history features rather than post content features (ablation) | Temporal-feature models · Weibo unfollow prediction | Precision: 9.35% | Improved |
| Remove unfollow-history features from the spatial-plus-content model (ablation) | UMHI · Weibo unfollow prediction | Recall: 0.8131 -> 0.8516 | Improved |
| Use post content features only rather than unfollow history features (ablation) | Temporal-feature models · Weibo unfollow prediction | Precision: 0.7701 -> 0.6766 | Hurt |
Closest papers by meaning
- Modeling Users’ Preferences and Social Links in Social Networking Services: A Joint-Evolving Perspective (AAAI 2016 · similarity 0.87)
- TSGAN: Temporal Social Graph Attention Network for Aggressive Behavior Forecasting (AAAI 2025 · similarity 0.85)
- Estimating Online Influence Needs Causal Modeling! Counterfactual Analysis of Misinformation Engagement on Social Media (AAAI 2026 · similarity 0.85)
- Decoupling User Relationships Guides Information Diffusion Prediction (Student Abstract) (AAAI 2024 · similarity 0.83)
- THGNets: Constrained Temporal Hypergraphs and Graph Neural Networks in Hyperbolic Space for Information Diffusion Prediction (AAAI 2025 · similarity 0.82)
- Correlation-Attention Masked Temporal Transformer for User Identity Linkage Using Heterogeneous Mobility Data (AAAI 2025 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
