Effect of training set size on SVM and Naïve Bayes for Twitter sentiment analysis.
Omar AbdelwahabMohamed BahgatChristopher J. LowranceAdel ElmaghrabyPublished in: ISSPIT (2015)
Keyphrases
- sentiment analysis
- training set size
- bayes classifiers
- tree augmented
- bayes classifier
- bayesian classifiers
- text classification
- naive bayes classifier
- social media content
- public opinion
- training set
- support vector machine
- opinion mining
- bayesian network classifiers
- multi class
- bayesian networks
- training data
- naive bayes
- sentiment classification
- support vector
- classification accuracy
- feature selection
- class distribution
- micro blog
- sentence level
- learning curves
- text mining
- decision trees
- generalization error
- logistic regression
- social media
- text categorization
- natural language processing
- machine learning
- step size
- decision forest
- knn
- product reviews
- learning curve
- online reviews
- labeled data
- social networks
- active learning
- cross validation
- sentiment lexicon