Senti-CS: Building a lexical resource for sentiment analysis using subjective feature selection and normalized Chi-Square-based feature weight generation.
Farhan Hassan KhanUsman QamarSaba BashirPublished in: Expert Syst. J. Knowl. Eng. (2016)
Keyphrases
- sentiment analysis
- chi square
- information gain
- feature selection
- text classification
- mutual information
- feature set
- opinion mining
- natural language processing
- sentiment classification
- product features
- feature subset
- text categorization
- logistic regression
- term frequency
- sentence level
- naive bayes
- sentiment polarity
- text mining
- decision trees
- correlation coefficient
- product reviews
- support vector
- machine learning
- image registration
- support vector machine
- feature vectors
- labeled data
- confidence intervals
- bag of words
- classification accuracy
- keywords
- similarity measure
- semantic relations
- n gram
- wordnet
- image classification
- feature space
- artificial intelligence