Feature selection using an improved Chi-square for Arabic text classification.
Said BahassineAbdellah MadaniMohammed Al-SaremMohamed KissiPublished in: J. King Saud Univ. Comput. Inf. Sci. (2020)
Keyphrases
- chi square
- text classification
- feature selection
- information gain
- term frequency
- text categorization
- mutual information
- logistic regression
- naive bayes
- bag of words
- text data
- feature set
- feature space
- text documents
- n gram
- classification accuracy
- support vector machine
- knn
- machine learning
- labeled data
- text mining
- information theoretic
- correlation coefficient
- support vector
- unlabeled data
- k nearest neighbor
- dimensionality reduction
- document collections
- feature extraction