Research map / Label-efficient and robust learning / Recognition and long-tail
Twitter Summarization Based on Social Network and Sparse Reconstruction
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 |
|---|---|---|---|
| add social (tweet-network) regularization (ablation) | SNSR · Twitter CTS | ROUGE-2 F: 0.10271 -> 0.13882 | Helped |
| add social regularization (ablation) | SNSR · Twitter CTS | ROUGE-1 F: 0.43236 -> 0.44887 | Helped |
| add diversity regularization (ablation) | SNSR · Twitter CTS | ROUGE-1 F: 0.40191 -> 0.44887 | Helped |
| add diversity regularization (ablation) | SNSR · Twitter CTS | ROUGE-2 F: 0.12940 -> 0.13882 | Helped |
| add group sparsity regularization (ablation) | SNSR · Twitter CTS | ROUGE-1 F: 0.43327 -> 0.44887 | Helped |
| add group sparsity regularization (ablation) | SNSR · Twitter CTS | ROUGE-SU4 F: 0.17749 -> 0.18147 | Helped |
| use SNSR instead of NNMF (best baseline) | text-only summarizers · Twitter CTS | ROUGE-1 F: 0.43784 -> 0.44887 | Helped |
| use SNSR instead of DSDR sparse reconstruction | DSDR · Twitter CTS | ROUGE-2 F: 0.12946 -> 0.13882 | Helped |
Closest papers by meaning
- TGSum: Build Tweet Guided Multi-Document Summarization Dataset (AAAI 2016 · similarity 0.88)
- MultiSum: A Multi-Facet Approach for Extractive Social Summarization Utilizing Semantic and Sociological Relationships (AAAI 2024 · similarity 0.87)
- Hashtag-Based Sub-Event Discovery Using Mutually Generative LDA in Twitter (AAAI 2016 · similarity 0.84)
- Unsupervised Summarization for Chat Logs with Topic-Oriented Ranking and Context-Aware Auto-Encoders (AAAI 2021 · similarity 0.84)
- Unsupervised Extractive Summarization with Learnable Length Control Strategies (AAAI 2024 · similarity 0.81)
- FedSum: Data-Efficient Federated Learning Under Data Scarcity Scenario for Text Summarization (AAAI 2025 · 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.