Finding optimal linear measures for feature selection in text categorization.
Elena MontañésElías F. CombarroJosé RanillaIrene DíazPublished in: SAC (2006)
Keyphrases
- text categorization
- finding optimal
- feature selection
- text classification
- information gain
- automated text categorization
- knn
- multi label
- feature weighting
- linear svm
- text documents
- naive bayes
- reuters corpus
- text filtering
- k nearest neighbor
- document frequency
- feature generation
- text classifiers
- semi supervised learning
- feature selection for text categorization
- feature selections
- feature selection and classifier
- similarity measure
- feature space
- unlabeled data
- automatic text categorization
- classification accuracy
- mutual information
- feature extraction
- dimensionality reduction
- term frequency
- training data
- machine learning
- feature reduction
- support vector machine