Research map / Label-efficient and robust learning / Recognition and long-tail
Semisupervised Autoencoder for Sentiment Analysis
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 ordinary reconstruction loss with classifier-guided Bregman loss | Denoising autoencoder · Amazon books | classification error rate: 15.10 -> 9.16 | Helped |
| replace ordinary reconstruction loss with classifier-guided Bregman loss | Denoising autoencoder · Amazon DVD | classification error rate: 15.64 -> 10.90 | Helped |
| replace ordinary reconstruction loss with classifier-guided Bregman loss | Denoising autoencoder · Amazon music | classification error rate: 15.44 -> 10.59 | Helped |
| replace ordinary reconstruction loss with classifier-guided Bregman loss | Denoising autoencoder · Amazon electronics | classification error rate: 14.74 -> 10.02 | Helped |
| replace ordinary reconstruction loss with classifier-guided Bregman loss | Denoising autoencoder · Amazon kitchenware | classification error rate: 12.48 -> 8.87 | Helped |
| replace ordinary reconstruction loss with classifier-guided Bregman loss | Denoising autoencoder · IMDB | classification error rate: 14.60 -> 10.52 | Helped |
| add supervised finetuning (ablation) | SBDAE · Sentiment benchmarks | classification error rate: 9.16 -> 9.12; 10.90 -> 10.90; 10.59 -> 10.58; 10.02 -> 10.01; 8.87 -> 8.83; 10.52 -> 10.50 | No clear effect |
| add unlabeled IMDB data after fitting the linear classifier | SBDAE · IMDB | classification error rate: 10.52 -> 10.42 | Helped |
Closest papers by meaning
- Learning Sentiment-Specific Word Embedding via Global Sentiment Representation (AAAI 2018 · similarity 0.85)
- Scaling and evaluating sparse autoencoders (ICLR 2025 · similarity 0.84)
- Revisiting LSTM Networks for Semi-Supervised Text Classification via Mixed Objective Function (AAAI 2019 · similarity 0.83)
- Identifying Sentiment Words Using an Optimization Model with L1 Regularization (AAAI 2016 · similarity 0.83)
- SASA: Subspace-Aware Sparse Autoencoders for Effective Mechanistic Interpretability (NeurIPS 2026 · similarity 0.83)
- Seek Common Ground While Reserving Differences: Semi-Supervised Image-Text Sentiment Recognition (CVPR 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.