A Technique for Improving the Performance of Naive Bayes Text Classification.
Yuqian JiangHuaizhong LinXuesong WangDongming LuPublished in: WISM (2) (2011)
Keyphrases
- text classification
- naive bayes
- text categorization
- naive bayes classifier
- bag of words
- logistic regression
- feature selection
- text classifiers
- uci datasets
- text documents
- uci data sets
- classification algorithm
- document classification
- text mining
- text data
- probability estimation
- naive bayesian classifier
- machine learning
- knn
- test instances
- bayesian classifier
- cost sensitive
- semantic features
- multi label
- unlabeled data
- labeled data
- decision trees
- term frequency
- co training
- k nearest neighbor
- independence assumption
- classification accuracy
- conditional independence assumption
- averaged one dependence estimators
- base classifiers
- data sets
- naive bayes classification