LDA-AdaBoost.MH: Accelerated AdaBoost.MH based on latent Dirichlet allocation for text categorization.
Bassam Al-SalemiMohd Juzaiddin Ab AzizShahrul Azman NoahPublished in: J. Inf. Sci. (2015)
Keyphrases
- latent dirichlet allocation
- text categorization
- boosting algorithms
- topic models
- feature selection
- multi class
- text classification
- topic modeling
- generative model
- naive bayes
- text mining
- knn
- text documents
- topic discovery
- lda model
- base classifiers
- latent topics
- learning algorithm
- cost sensitive
- k nearest neighbor
- support vector
- gibbs sampling
- multi label
- dimensionality reduction
- decision trees
- document classification
- variational bayesian inference
- weak classifiers
- training data
- generalization error
- feature extraction
- text classifiers
- transfer learning
- text collections
- semi supervised learning
- probabilistic topic models
- support vector machine
- n gram
- keywords
- labeled data
- feature space
- prior knowledge
- nearest neighbor