Interactions Between Document Representation and Feature Selection in Text Categorization.
Milos RadovanovicMirjana IvanovicPublished in: DEXA (2006)
Keyphrases
- text categorization
- document representation
- text documents
- feature selection
- document categorization
- document frequency
- text classification
- bag of words
- term frequency
- document clustering
- information gain
- text data
- data fusion
- language model
- web documents
- vector space
- knn
- document collections
- tf idf
- data sets
- vector space model
- feature extraction
- feature selections
- machine learning
- semantic information
- semi supervised learning
- k nearest neighbor
- co occurrence
- probabilistic model
- object recognition
- unlabeled data
- unsupervised learning
- feature set
- domain knowledge
- decision trees
- learning algorithm
- information retrieval