Research map / Learning theory and algorithms / Combinatorial and search optimization
Identifying Sentiment Words Using an Optimization Model with L1 Regularization
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 |
|---|---|---|---|
| Use ISOMER instead of SO-PMI | sentiment word identification · Cornell | F-score: 0.4775 -> 0.5150 | Helped |
| Use ISOMER instead of COM | sentiment word identification · Stanford | F-score: 0.4556 -> 0.5243 | Helped |
| Use ISOMER instead of COM | sentiment word identification · Chinese | F-score: 0.5041 -> 0.5358 | Helped |
| Use ISOMER instead of SO-PMI | sentiment word identification · Chinese | F-score: 0.4777 -> 0.5358 | Helped |
| Use COM instead of SO-PMI | sentiment word identification · Chinese | F-score: 0.4777 -> 0.5041 | Helped |
| Use SO-PMI instead of COM | sentiment word identification · Cornell | F-score: 0.4497 -> 0.4775 | Helped |
| Vary lambda between seed-word-only (0) and document-only (1) likelihood (ablation) | ISOMER · Cornell, Stanford, Chinese | F-score | Helped |
| Increase regularizer beta (ablation) | ISOMER · Cornell, Stanford, Chinese | density of selected words | Helped |
| Use ISOMER lexicon words as features instead of SO-PMI | SVM document classifier · Cornell (TF-IDF) | precision: 0.685 -> 0.816 | Helped |
| Use ISOMER lexicon words as features instead of COM | SVM document classifier · Stanford (TF-IDF) | precision: 0.631 -> 0.757 | Helped |
| Use ISOMER lexicon words instead of CHI features | SVM document classifier · Chinese (BM25) | precision: 0.912 -> 0.916 | Helped |
| Use ISOMER words instead of COM words | SVM document classifier · Chinese (TF-IDF) | precision: 0.834 -> 0.908 | Helped |
Closest papers by meaning
- Semisupervised Autoencoder for Sentiment Analysis (AAAI 2016 · similarity 0.83)
- Learning Sentiment-Specific Word Embedding via Global Sentiment Representation (AAAI 2018 · similarity 0.83)
- Aspect-Based Sentiment Analysis with Explicit Sentiment Augmentations (AAAI 2024 · similarity 0.83)
- Intelligent Calibration for Bias Reduction in Sentiment Corpora Annotation Process (AAAI 2024 · similarity 0.81)
- DanceHA: A Multi-Agent Framework for Document-Level Aspect-Based Sentiment Analysis (AAAI 2026 · similarity 0.80)
- SimRP: Syntactic and Semantic Similarity Retrieval Prompting Enhances Aspect Sentiment Quad Prediction (AAAI 2025 · similarity 0.80)
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.