Unsupervised collective-based framework for dynamic retraining of supervised real-time spam tweets detection model

作者：

Highlights：

• Collective-based tweets analysis for retraining real-time spam tweet classifier.

• Leveraging simple tweet meta-data for providing periodic annotated spam data-sets.

• Our method provides high spam recall values, allowing to adapt social spammers.

• Outperforming the performance of two real-time spam detection cutting edge methods.

摘要

•Collective-based tweets analysis for retraining real-time spam tweet classifier.•Leveraging simple tweet meta-data for providing periodic annotated spam data-sets.•Our method provides high spam recall values, allowing to adapt social spammers.•Outperforming the performance of two real-time spam detection cutting edge methods.

论文关键词：Twitter,Real-time,Spam,Social spammers,Twitter stream

论文评审过程：Received 26 June 2018, Revised 4 April 2019, Accepted 29 May 2019, Available online 6 June 2019, Version of Record 14 June 2019.

论文官网地址：https://doi.org/10.1016/j.eswa.2019.05.052