朴素贝叶斯反垃圾邮件过滤器的评估
计算与语言
2009-09-25 v1 人工智能
摘要
最近有人认为，朴素贝叶斯分类器可用于过滤不 solicited bulk e-mail（“垃圾邮件”）。我们在我们公开可用的语料库上对该提案进行彻底评估，为标准基准做出了贡献。同时我们研究了属性集大小、训练语料库大小、词形还原和停用词表对过滤器性能的影响，这些问题此前未被探索。 After introducing appropriate cost-sensitive evaluation measures, we reach the conclusion that additional safety nets are needed for the Naive Bayesian anti-spam filter to be viable in practice.
引用
@article{arxiv.cs/0006013,
title = {An evaluation of Naive Bayesian anti-spam filtering},
author = {Ion Androutsopoulos and John Koutsias and Konstantinos V. Chandrinos and George Paliouras and Constantine D. Spyropoulos},
journal= {arXiv preprint arXiv:cs/0006013},
year = {2009}
}
备注
9 pages