Document classification with supervised latent feature selection.
Ondrej HavaMiroslav SkrbekPavel KordíkPublished in: WIMS (2012)
Keyphrases
- document classification
- feature selection
- text categorization
- text classification
- latent structure
- text documents
- unsupervised learning
- text mining
- classification accuracy
- latent variables
- linear classification
- machine learning
- support vector machine
- naive bayes
- topic extraction
- support vector
- knn
- feature set
- classification algorithm
- web documents
- feature space
- n gram
- real world
- model selection
- dimensionality reduction
- supervised learning
- feature extraction
- learning algorithm
- k nearest neighbor
- labeled data
- nearest neighbor
- small number
- reinforcement learning
- decision trees
- information retrieval
- databases
- automatic document classification