Research map / Label-efficient and robust learning / Recognition and long-tail
Sentiment Analysis via Deep Hybrid Textual-Crowd Learning Model
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 |
|---|---|---|---|
| replace majority-vote aggregation with joint probabilistic coupling (CrowdDeepAE vs MV-DeepAE) (ablation) | deep autoencoder text model · CF (20% labels) | accuracy: 0.682 -> 0.790 | Helped |
| replace majority-vote aggregation with joint coupling (CrowdDeepAE vs MV-DeepAE) (ablation) | deep autoencoder text model · SP (20% labels) | accuracy: 0.738 -> 0.816 | Helped |
| replace majority-vote aggregation with joint coupling (CrowdDeepAE vs MV-DeepAE) (ablation) | deep autoencoder text model · SP (all labels) | accuracy: 0.885 -> 0.915 | Helped |
| add text data via deep autoencoder to crowd aggregation (vs crowd-only models) | crowd aggregation · CF (20% labels) | accuracy: 0.688 -> 0.790 | Helped |
| deep autoencoder text model instead of shallow bag-of-words text model | hybrid crowd-text model · CF (20% labels) | accuracy: 0.715 -> 0.790 | Helped |
| CrowdDeepAE vs best baselines with all crowd labels | crowd aggregation · SP (all labels) | accuracy: 0.915 -> 0.915 | No clear effect |
| CrowdDeepAE vs best baseline with all crowd labels | crowd aggregation · CF (all labels) | accuracy: 0.890 -> 0.912 | Helped |
| CrowdDeepAE vs BCCwords on NLPD with all labels | crowd aggregation · CF (all labels) | NLPD (lower better): 0.591 -> 0.479 | Helped |
Closest papers by meaning
- Practical Sentiment Analysis for Education: The Power of Student Crowdsourcing (AAAI 2024 · similarity 0.87)
- Semi-Supervised Learning From Crowds Using Deep Generative Models (AAAI 2018 · similarity 0.85)
- Coupled Confusion Correction: Learning from Crowds with Sparse Annotations (AAAI 2024 · similarity 0.83)
- Unbiased Multi-Label Learning from Crowdsourced Annotations (ICML 2024 · similarity 0.83)
- Label Aggregation for Composite Crowd Tasks by Worker Ability Constraint Satisfaction (AAAI 2025 · similarity 0.82)
- Evaluating LLM-contaminated Crowdsourcing Data Without Ground Truth (NeurIPS 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.