ECNU: Multi-level Sentiment Analysis on Twitter Using Traditional Linguistic Features and Word Embedding Features.
Zhihua ZhangGuoShun WuMan LanPublished in: SemEval@NAACL-HLT (2015)
Keyphrases
- sentiment analysis
- sentence level
- linguistic features
- product features
- opinion mining
- text classification
- sentiment classification
- linguistic knowledge
- public opinion
- social media content
- structural features
- feature set
- natural language processing
- low level
- social media
- feature extraction
- co occurrence
- machine learning
- text mining
- multi document summarization
- semantic information
- novelty detection
- named entities
- feature vectors
- feature selection
- artificial intelligence