Putting Sarcasm Detection into Context: The Effects of Class Imbalance and Manual Labelling on Supervised Machine Classification of Twitter Conversations.
Gavin AbercrombieDirk HovyPublished in: ACL (Student Research Workshop) (2016)
Keyphrases
- class imbalance
- class distribution
- cost sensitive
- imbalanced datasets
- cost sensitive learning
- active learning
- feature selection
- high dimensionality
- sampling methods
- majority class
- supervised learning
- class labels
- concept drift
- unsupervised learning
- imbalanced data
- minority class
- data sets
- class imbalanced
- decision trees
- benchmark datasets
- feature extraction
- support vector
- pattern recognition
- high dimensional
- error prone
- text classification
- feature vectors
- support vector machine
- multi class
- classification algorithm