Factorial design analysis applied to the performance of SMS anti-spam filtering systems
作者：
Highlights：
• An anti-spam filtering system for SMS is proposed.
• Different system parameters are evaluated through factorial design analysis.
• The optimal configuration has reached over 98% classification accuracy.
• The number of features increases system performance but adds computational cost.
• Linguistic techniques do not represent significant performance boost for some setups.
摘要
•An anti-spam filtering system for SMS is proposed.•Different system parameters are evaluated through factorial design analysis.•The optimal configuration has reached over 98% classification accuracy.•The number of features increases system performance but adds computational cost.•Linguistic techniques do not represent significant performance boost for some setups.
论文关键词：Spam filtering,Factorial design,Support vector machine (SVM),Naive bayesian (NB),Short message service (SMS)
论文评审过程：Received 12 September 2015, Revised 6 August 2016, Accepted 7 August 2016, Available online 8 August 2016, Version of Record 11 August 2016.
论文官网地址：https://doi.org/10.1016/j.eswa.2016.08.038
