Wikipedia: Sentiment analysis (also known as opinion mining) refers to the use of natural language processing, text analysis and computational linguistics to identify and extract subjective information in source materials.
In 1997, firstly proposed by MIT Professor Rosalind Picard in Effective Computing.
Basic task is classifying the polarity (positive, negative, or neutral). beyond polarity: e.g. emotional states such angry, sad, and happy. Higher: sarcasm?
Application and methodologies:
- Product, restaurant, or film review rating prediction.
Most statistical classification methods ignore the neutral class.
- Use a scaling system, give the words an associated number on a -10 to +10 scale.
- Another direction is subjective/objective identification. Remove objective sentences improve the polarity classification performance.
- A more fine-grained analysis model is called the feature/aspect-based sentiment analysis.
Chinese Sentiment Dictionary and Resources
Stanford NLP cource on Coursera (Class 7) --> Sentiment Analysis introduced the resources and methods
Query:
Whose sentiment is able to predict the stock movement better? How to find out them?