HR-CTC: A Large Human Resource Corpus for Text Classification.
Haoyu XuChongyang GuHan ZhouJunjie ZhangPublished in: CoRR (2017)
Keyphrases
- human resources
- text classification
- training corpus
- text data
- naive bayes
- text categorization
- developing countries
- bag of words
- text mining
- feature selection
- human resource management
- n gram
- text classifiers
- training documents
- machine learning
- labeled data
- text documents
- sentiment analysis
- high resolution
- data cleaning
- semantic features
- knn
- class distribution
- unlabeled data
- sentiment classification
- low resolution
- e learning
- training data
- multi label
- domain knowledge
- human capital
- test set
- human resources management