Dimension reduction using least squares regression in multi-labeled text categorization.
Cheong Hee ParkPublished in: CIT (2008)
Keyphrases
- text categorization
- dimension reduction
- feature selection
- unlabeled documents
- training documents
- feature extraction
- multi label
- text classification
- high dimensionality
- principal component analysis
- knn
- text documents
- high dimensional
- high dimensional data
- k nearest neighbor
- cluster analysis
- semi supervised learning
- linear discriminant analysis
- singular value decomposition
- feature space
- automatic text categorization
- low dimensional
- unsupervised learning
- preprocessing
- information gain
- naive bayes
- reuters corpus
- feature selection for text categorization
- dimensionality reduction
- training data
- classify documents
- supervised learning
- data analysis
- computer vision
- class labels
- unlabeled data
- feature set
- classification accuracy
- object recognition
- image segmentation
- machine learning
- neural network