Customized crowds and active learning to improve classification
作者：
Highlights：
• Crowdsourcing as data source for classification.
• Capture the drift in user preferences in a recommendation system.
• Apply active strategies for adaptation to each user.
• Crowdsourcing to avoid excessive user feedback.
• Case study on humor classification.
摘要
•Crowdsourcing as data source for classification.•Capture the drift in user preferences in a recommendation system.•Apply active strategies for adaptation to each user.•Crowdsourcing to avoid excessive user feedback.•Case study on humor classification.
论文关键词：Crowdsourcing,Active learning,Classification
论文评审过程：Available online 9 July 2013.
论文官网地址：https://doi.org/10.1016/j.eswa.2013.06.072
