Повышение качества классификации текстов путем модификации обучающего множества (Improvement of Text Classification Quality by Modifying the Training Set).
Anton KolesovPublished in: RCDL (2012)
Keyphrases
- text classification
- training set
- quality improvement
- feature selection
- text mining
- machine learning
- classification accuracy
- quality assessment
- high quality
- test set
- text documents
- text categorization
- bag of words
- data quality
- multi label
- sentiment analysis
- quality measures
- naive bayes
- data sets
- active learning
- feature space
- neural network
- database
- training samples
- labeled data
- class labels
- cross validation
- supervised learning
- nearest neighbor
- knn
- data analysis
- text data
- active appearance models