Research map / Video / Video-language understanding
FakeSV: A Multimodal Benchmark with Rich Social Context for Fake News Detection on Short Video Platforms
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 SV-FEND's multimodal content and social-context fusion instead of the strongest reported single-modality BERT baseline | FakeSV · FakeSV event-level five-fold CV | accuracy: 76.82$_{\pm3.33}$ -> 79.31$_{\pm2.75}$ | Helped |
| add news content (ablation) | SV-FEND · FakeSV event-level five-fold CV | accuracy: 74.89 -> 79.31 | Helped |
| add text (ablation) | SV-FEND · FakeSV event-level five-fold CV | accuracy: 75.37 -> 79.31 | Helped |
| add title (ablation) | SV-FEND · FakeSV event-level five-fold CV | accuracy: 77.28 -> 79.31 | Helped |
| add transcript (ablation) | SV-FEND · FakeSV event-level five-fold CV | accuracy: 77.89 -> 79.31 | Helped |
| add visual features (ablation) | SV-FEND · FakeSV event-level five-fold CV | accuracy: 77.97 -> 79.31 | Helped |
| add keyframes (ablation) | SV-FEND · FakeSV event-level five-fold CV | accuracy: 78.49 -> 79.31 | Helped |
| add video clips (ablation) | SV-FEND · FakeSV event-level five-fold CV | accuracy: 78.95 -> 79.31 | Helped |
| add audio (ablation) | SV-FEND · FakeSV event-level five-fold CV | accuracy: 78.95 -> 79.31 | Helped |
| add social context (ablation) | SV-FEND · FakeSV event-level five-fold CV | accuracy: 78.62 -> 79.31 | Helped |
| add user features (ablation) | SV-FEND · FakeSV event-level five-fold CV | accuracy: 78.76 -> 79.31 | Helped |
| add comments (ablation) | SV-FEND · FakeSV event-level five-fold CV | accuracy: 79.09 -> 79.31 | Helped |
Closest papers by meaning
- External Reliable Information-enhanced Multimodal Contrastive Learning for Fake News Detection (AAAI 2025 · similarity 0.88)
- DAMMFND: Domain-Aware Multimodal Multi-view Fake News Detection (AAAI 2025 · similarity 0.88)
- Each Fake News Is Fake in Its Own Way: An Attribution Multi-Granularity Benchmark for Multimodal Fake News Detection (AAAI 2025 · similarity 0.88)
- Text-Guided Fine-grained Counterfactual Inference for Short Video Fake News Detection (AAAI 2025 · similarity 0.88)
- Learning Complex Heterogeneous Multimodal Fake News via Social Latent Network Inference (AAAI 2025 · similarity 0.87)
- Bad Actor, Good Advisor: Exploring the Role of Large Language Models in Fake News Detection (AAAI 2024 · similarity 0.86)
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.