Research map / Label-efficient and robust learning / Recognition and long-tail
SNNN: Promoting Word Sentiment and Negation in Neural Sentiment Classification
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 word sentiment and negation attention instead of general attention (ablation) | LSTM+A · Yelp 2015 | accuracy: 0.678 -> 0.704 | Helped |
| add word sentiment and negation attention instead of general attention (ablation) | LSTM+A · IMDB | accuracy: 0.462 -> 0.535 | Helped |
| add negation embedding to LSTM (ablation) | LSTM · Yelp 2015 | accuracy: 0.675 -> 0.687 | Helped |
| add sentiment embedding to LSTM (ablation) | LSTM · Yelp 2015 | accuracy: 0.675 -> 0.688 | Helped |
| add negation attention to LSTM (ablation) | LSTM+A · Yelp 2015 | accuracy: 0.678 -> 0.695 | Helped |
| embed both sentiment and negation simultaneously instead of one (ablation) | LSTM+A · Yelp 2015 | accuracy: 0.695 -> 0.678 | Hurt |
| embed both sentiment and negation (no attention) vs LSTM (ablation) | LSTM · Yelp 2015 | accuracy: 0.675 -> 0.665 | Hurt |
| embed both sentiment and negation, IMDB accuracy (ablation) | LSTM · IMDB | accuracy: 0.432 -> 0.456 | No clear effect |
| also embed negation when using negation attention (ablation) | LSTM+NA · Yelp 2015 | accuracy: 0.695 -> 0.691 | No clear effect |
| add attention to LSTM (ablation) | LSTM · Yelp 2015 | accuracy: 0.675 -> 0.678 | Helped |
| add attention to LSTM (ablation) | LSTM · IMDB | accuracy: 0.432 -> 0.462 | Helped |
| add sentiment attention to LSTM (ablation) | LSTM+A · IMDB | accuracy: 0.462 -> 0.473 | Helped |
Closest papers by meaning
- Improving Review Representations With User Attention and Product Attention for Sentiment Classification (AAAI 2018 · similarity 0.86)
- Learning to Attend via Word-Aspect Associative Fusion for Aspect-Based Sentiment Analysis (AAAI 2018 · similarity 0.85)
- Targeted Aspect-Based Sentiment Analysis via Embedding Commonsense Knowledge into an Attentive LSTM (AAAI 2018 · similarity 0.85)
- TopicRNN: A Recurrent Neural Network with Long-Range Semantic Dependency (ICLR 2017 · similarity 0.85)
- Replicate, Walk, and Stop on Syntax: An Effective Neural Network Model for Aspect-Level Sentiment Classification (AAAI 2020 · similarity 0.85)
- Exploring Model Editing for LLM-based Aspect-Based Sentiment Classification (AAAI 2025 · similarity 0.84)
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.