Conducting sparse feature selection on arbitrarily long phrases in text corpora with a focus on interpretability.
Luke MiratrixRobin AckermanPublished in: Stat. Anal. Data Min. (2016)
Keyphrases
- text corpora
- feature selection
- word pairs
- text mining
- text documents
- text categorization
- computational linguistics
- text classifiers
- text analysis
- text classification
- feature space
- machine learning
- topic models
- topic modeling
- text collections
- dimensionality reduction
- high dimensional
- support vector
- document collections
- feature set
- active learning
- decision trees