Active learning for text classification with reusability
作者：
Highlights：
• We investigate the reusability problem in active learning for text classification.
• The reusability problem affects active learning systems for text classification.
• If the consumer classifier type is known, it should be used for the selector.
• Local and global classifiers do not mix well with regard to reusability.
• To maximize reusability support vector machines should be used as selectors.
摘要
•We investigate the reusability problem in active learning for text classification.•The reusability problem affects active learning systems for text classification.•If the consumer classifier type is known, it should be used for the selector.•Local and global classifiers do not mix well with regard to reusability.•To maximize reusability support vector machines should be used as selectors.
论文关键词：Active learning,Machine learning,Reusability problem,Text classification
论文评审过程：Received 8 June 2014, Revised 1 October 2015, Accepted 2 October 2015, Available online 19 October 2015, Version of Record 10 November 2015.
论文官网地址：https://doi.org/10.1016/j.eswa.2015.10.003
