Research map / Large language models / Language, safety and interpretability
SenticNet 5: Discovering Conceptual Primitives for Sentiment Analysis by Means of Context Embeddings
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 biLSTM context embeddings instead of skipgram-based context for lexical substitution | lexical substitution · LST-07 | GAP: 55.1% -> 58.55% | Helped |
| use biLSTM context embeddings instead of skipgram-based context for lexical substitution | lexical substitution · LST-14 | GAP: 53.6% -> 56.25% | Helped |
| replace SenticNet 4 with SenticNet 5 (conceptual primitives) in sentic patterns | Sentic Patterns · Blitzer Dataset | accuracy: 91.3% -> 94.6% | Helped |
| replace SenticNet 4 with SenticNet 5 (conceptual primitives) in sentic patterns | Sentic Patterns · Movie Review Dataset | accuracy: 90.1% -> 92.8% | Helped |
Closest papers by meaning
- Targeted Aspect-Based Sentiment Analysis via Embedding Commonsense Knowledge into an Attentive LSTM (AAAI 2018 · similarity 0.88)
- Understanding the Semantic Content of Sparse Word Embeddings Using a Commonsense Knowledge Base (AAAI 2020 · similarity 0.86)
- Deep contextualized word representations (ICLR 2018 · similarity 0.85)
- ConceptNet 5.5: An Open Multilingual Graph of General Knowledge (AAAI 2017 · similarity 0.85)
- How recurrent networks implement contextual processing in sentiment analysis (ICML 2020 · similarity 0.85)
- Concept-Guided Interpretability via Neural Chunking (NeurIPS 2025 · similarity 0.83)
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.