The Impact of Pre-processing on the Classification of MEDLINE Documents.
Carlos Adriano GonçalvesCélia Talma GonçalvesRui CamachoEugénio C. OliveiraPublished in: PRIS (2010)
Keyphrases
- preprocessing
- document classification
- feature extraction
- document collections
- pattern recognition
- decision trees
- support vector
- classification accuracy
- automatic classification
- pre classified
- web documents
- image classification
- data pre processing
- document retrieval
- feature selection
- text classification
- support vector machine svm
- information retrieval
- latent semantic indexing
- automatic categorization
- classification method
- text mining
- data mining
- machine learning
- class labels
- classification algorithm
- retrieval systems
- supervised learning
- multi class
- support vector machine
- xml documents
- keywords
- metadata