How Spam Features Change in Twitter and the Impact to Machine Learning Based Detection

被引：1

作者：

Wu, Tingmin ^{[1
]}

Wang, Derek ^{[1
]}

Wen, Sheng ^{[1
]}

Xiang, Yang ^{[1
]}

机构：

[1] Swinburne Univ Technol, Hawthorn, Vic 3122, Australia

来源：

INFORMATION SECURITY PRACTICE AND EXPERIENCE, ISPEC 2017 | 2017年 / 10701卷

关键词：

Security; Spam; Twitter;

D O I：

10.1007/978-3-319-72359-4_57

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Twitter Spam is a critical problem and current solution is mainly about machine learning based detection. However, recent studies found that the spam features are continuously changing day by day (called 'Spam Drift' problem), which may significantly affect the performance of the detection. In this paper, we carried out a real-data driven study to explored the 'Spam Drift' problem and its impact to machine learning based detection. Our study found that only a small group of spam features will continuously change. The results also suggested a counter-intuitive conclusion that the 'Spam Drift' problem does not have serious impact on spam detection Precision (SP) and non-spam detection Recall (NR), two metrics that industries prioritise in practice.

引用

页码：898 / 904

页数：7