A utility-theoretic ranking method for semi-automated text classification.
Giacomo BerardiAndrea EsuliFabrizio SebastianiPublished in: SIGIR (2012)
Keyphrases
- semi automated
- text classification
- fully automated
- text categorization
- text mining
- feature selection
- labeled data
- text documents
- text classifiers
- sentiment analysis
- bag of words
- machine learning
- n gram
- knn
- text data
- document classification
- naive bayes
- utility function
- semantic features
- multi label
- unlabeled data
- language modeling
- real world
- association rules
- text classification tasks