Cost sensitive hierarchical document classification to triage PubMed abstracts for manual curation.
Emily SeymourRohini DamleAlessandro SetteBjoern PetersPublished in: BMC Bioinform. (2011)
Keyphrases
- document classification
- cost sensitive
- multi class
- text categorization
- misclassification costs
- classification algorithm
- cost sensitive learning
- naive bayes
- text classification
- text mining
- cost sensitive classification
- text documents
- class distribution
- web documents
- text analysis
- multi label
- information extraction
- support vector machine
- active learning
- natural language processing
- pairwise
- keywords
- information retrieval systems
- knowledge representation
- artificial intelligence