Estimating the Expected Effectiveness of Text Classification Solutions under Subclass Distribution Shifts.
Nedim LipkaBenno SteinJames G. ShanahanPublished in: ICDM (2012)
Keyphrases
- text classification
- text categorization
- feature selection
- database
- bag of words
- naive bayes
- text mining
- optimal solution
- data mining
- semantic features
- data cleaning
- machine learning
- np complete
- neural network
- n gram
- extreme values
- text data
- sentiment analysis
- text documents
- data distribution
- multi label
- search engine
- artificial intelligence
- databases