AuDoLab: Automatic document labelling and classification for extremely unbalanced data.
Arne TillmannAnton ThielmannGillian KantChristoph WeisserBenjamin SäfkenAlexander SilbersdorffThomas KneibPublished in: J. Open Source Softw. (2021)
Keyphrases
- unbalanced data
- support vector machine
- classification accuracy
- training data
- decision trees
- support vector
- information retrieval
- pattern recognition
- ridge regression
- training set
- feature selection
- classification algorithm
- image classification
- text documents
- information retrieval systems
- class labels
- learning algorithm
- decision rules
- text classification
- multi class
- feature vectors
- feature space
- keywords