Research map / Graph learning / Graph self-supervised learning
Public Opinion Field Effect Fusion in Representation Learning for Trending Topics Diffusion
Junliang Li, Yajun Yang, Qinghua Hu, Xin Wang, Hong Gao
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 |
|---|---|---|---|
| use POFD instead of best baseline (HALO) | POFD · BuzzFeed link prediction | AUC (%): 94.32 -> 96.36 | Improved |
| use POFD instead of best baseline | POFD · PolitiFact link prediction | AUC (%): 93.88 -> 95.44 | Improved |
| use POFD instead of best baseline | POFD · Twitter link prediction | AP (%): 92.82 -> 94.99 | Improved |
| use POFD instead of best baseline (MetaHG) | POFD · BuzzFeed event classification | F1 (%): 84.62 -> 92.31 | Improved |
| use POFD instead of best baseline | POFD · Twitter event classification | ACC (%): 83.33 -> 85.31 | Improved |
| use POFD instead of best baseline (HALO) | POFD · DBLP node classification | Macro-F1 (%): 92.81 -> 95.03 | Improved |
| GNN encoders instead of random-walk methods | GNN baselines · link prediction | AUC (%): 76.12 -> 92.87 | Improved |
| remove social circle influence (POFDtp) (ablation) | POFD · BuzzFeed | AUC/AP/ACC/F1 | Improved |
| remove topic propagation, replace with GAT (POFDsci) (ablation) | POFD · BuzzFeed | AUC/AP/ACC/F1 | Improved |
| remove unsupervised proximity loss (POFDloss) (ablation) | POFD · BuzzFeed | AUC/AP/ACC/F1 | Improved |
| use 2-hop neighbors instead of 1-hop for pof (ablation) | POFD · BuzzFeed | AUC (%): 96.36 -> 93.18 | Hurt |
| use 4-hop neighbors instead of 1-hop (ablation) | POFD · Twitter | AP (%): 94.99 -> 80.40 | Hurt |
Closest papers by meaning
- Public Opinion Field Effect and Hawkes Process Join Hands for Information Popularity Prediction (AAAI 2025 · similarity 0.88)
- Opinion Maximization in Social Networks by Modifying Internal Opinions (NeurIPS 2025 · similarity 0.82)
- CasFT: Future Trend Modeling for Information Popularity Prediction with Dynamic Cues-Driven Diffusion Models (AAAI 2025 · similarity 0.82)
- Enhancing Multi-Scale Diffusion Prediction via Sequential Hypergraphs and Adversarial Learning (AAAI 2024 · similarity 0.82)
- Improving Multimodal Social Media Popularity Prediction via Selective Retrieval Knowledge Augmentation (AAAI 2025 · similarity 0.81)
- Non-Euclidean Mixture Model for Social Network Embedding (NeurIPS 2024 · similarity 0.81)
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.
