Improving text classification with word embedding.
Lihao GeTeng-Sheng MohPublished in: IEEE BigData (2017)
Keyphrases
- text classification
- n gram
- term frequency
- training corpus
- text categorization
- distributional clustering
- word segmentation
- text data
- feature selection
- machine learning
- sentiment analysis
- text mining
- bag of words
- labeled data
- knn
- vector space
- sentiment classification
- data cleaning
- naive bayes
- word recognition
- text documents
- neural network
- information theoretic
- co occurrence
- document classification
- multi label
- information extraction
- semantic features
- keywords