Research map / Graph learning / Graph self-supervised learning
Public Wisdom Matters! Discourse-Aware Hyperbolic Fourier Co-Attention for Social Text Classification
Karish Grover, S M Phaneendra Angara, Md Shad Akhtar, Tanmoy Chakraborty
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 |
|---|---|---|---|
| add public comments (discourse) to the source post (ablation) | Hyphen-hyperbolic · Politifact | F1: 0.8963 -> 0.9686 (7.23% drop without comments) | Improved |
| add public comments (discourse) to the source post (ablation) | Hyphen-hyperbolic · Gossipcop | F1: 0.7407 -> 0.8167 | Improved |
| add public comments (discourse) to the source post (ablation) | Hyphen-hyperbolic · ANTiVax | F1: 1.05% drop without comments | Improved |
| add public comments (discourse) to the source post (ablation) | Hyphen-hyperbolic · Pheme | F1: 0.8017 -> 0.8757 | Improved |
| add public comments (discourse) to the source post (ablation) | Hyphen-hyperbolic · FigLang Twitter | F1: 0.7375 -> 0.8222 | Improved |
| add the Fourier transform layer (ablation) | Hyphen-hyperbolic · Gossipcop | F1: 0.7607 -> 0.8167 (5.60% drop without) | Improved |
| add the Fourier transform layer (ablation) | Hyphen-hyperbolic · Politifact | F1: 0.9512 -> 0.9686 (1.74% drop without) | Improved |
| add the Fourier transform layer (ablation) | Hyphen-hyperbolic · ANTiVax | F1: 0.87% F1 gain | Improved |
| add the Fourier transform layer (ablation) | Hyphen-euclidean · Gossipcop | F1: 0.7584 -> 0.7812 (2.28%) | Improved |
| use hyperbolic manifold instead of Euclidean | Hyphen · Gossipcop | F1: 0.781 -> 0.816 (3.55%) | Improved |
| use hyperbolic manifold instead of Euclidean | Hyphen · Politifact | F1: 0.940 -> 0.968 (2.85%) | Improved |
| use hyperbolic manifold instead of Euclidean | Hyphen · ANTiVax | F1: 0.937 -> 0.945 (0.83%) | Improved |
Closest papers by meaning
- Towards Effective, Efficient and Unsupervised Social Event Detection in the Hyperbolic Space (AAAI 2025 · similarity 0.86)
- Sparse Autoencoders for Hypothesis Generation (ICML 2025 · similarity 0.84)
- Multi-Modal Discussion Transformer: Integrating Text, Images and Graph Transformers to Detect Hate Speech on Social Media (AAAI 2024 · similarity 0.83)
- Language Model Meets Prototypes: Towards Interpretable Text Classification Models through Prototypical Networks (AAAI 2025 · similarity 0.82)
- Bad Actor, Good Advisor: Exploring the Role of Large Language Models in Fake News Detection (AAAI 2024 · similarity 0.82)
- Learning Complex Heterogeneous Multimodal Fake News via Social Latent Network Inference (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.
