由於網路平台的大幅擴張，網軍(Internet army)這個工作也隨之
增加，公關公司會付錢給學生或無工作者，讓他們發文或回覆
來影響輿論風向。
PTT 在台灣是相當大的網路平台，由於其匿名性以及能見度
高，大量的網軍因此將這個平台視為主要的攻擊對象，許多網
軍會針對特殊議題進行帶風向。
因此，找到一種方法來偵測匿名平台中的網軍是很重要的議
題。在此篇研究中，I.A.D 系統針對網軍進行分析獲得數個網
軍的特徵，並藉由網軍特徵建立預測模型，使系統能夠判斷使
用者是否是網軍。

As the expansion of online social network, the occupation number of Internet
army has increased. Students or unemployed post some article or reply to get
paid by public relationship company, who are also known as paid poster,
would impact peoples’ opinions.
In Taiwan, PTT is such a large platform with anonymity and visibility.
Because of influence of PTT, it has become a main target of Internet armies.
Therefore, it is an important issue to find out a method to detect Internet
armies on anonymous platform. In this research, I.A.D. system(Internet
Armies Detection) analyze and find out some the features of Internet army. In
addition, I.A.D. also build predicted models by features of Internet army. This
makes the system to identify whether a user is Internet army or not.

1. https://www.bbc.com/news/election-us-2020-54811410
2. https://www.usnews.com/news/politics/articles/2021-05-26/russia-still-largestdriver-of-disinformation-on-social-media-facebook-report-finds
3. Cheng Chen, Kui Wu ,Venkatesh Srinivasan ,Xudong Zhang. ”Battling the Internet
Water Army: Detection of Hidden Paid Posters “ in 2013 IEEE/ACM International
Conference on Advances in Social Networks Analysis and Mining
4. Guirong Chen, Wandong Cai, Jiuming Huang, Xianlong Jiao.” Uncovering and
Characterizing Internet Water Army in Online Forums ” in 2016 IEEE First
International Conference on Data Science in Cyberspace
5. A. E. Azab, A. M. Idrees, M. A. Mahmoud, and H. Hefny, "Fake Account
Detection in Twitter Based on Minimum Weighted Feature set," International
Journal of Computer, Electrical, Automation, Control and Information Engineering,
vol. 10, no. 1, pp. 13-18, 201
6. S. Crescia, R. D. Pietrob, M. Petrocchia, A. Spognardia and M. Tesconia, "Fame
for sale: efficient detection of fake Twitter followers," Decision Support Systems,
vol. 80, pp. 56-71, 2015.
7. S. Khaled, H. M. O. Mokhtar, and N. El-Tazi, "Detecting Fake Accounts on Social
Media," in 2018 IEEE International Conference on Big Data (Big Data), Seattle,
WA, USA, 2018.
27
8. A. Gupta and R. Kaushal, "Towards Detecting Fake User Accounts in Facebook,"
2017
9. Sarah Khaled, Neamat El-Tazi, Hoda M. O. Mokhtar. “Detecting Fake Accounts on
Social Media ”2018 IEEE International Conference on Big Data (Big Data)
10. Qiang Cao, Xiaowei Yang, Jieqi Yu, Christopher Palow. “Uncovering Large
Groups of Active Malicious Accounts in Online Social Networks” Proceedings of
the 2014 ACM SIGSAC Conference on Computer and Communications Security.
November 2014 Pages 477–488
11. Hacking Financial Market. 2016. http://goo.gl/4AkWyt
12. Kurt Thomas, Chris Grier, Justin Ma, Vern Paxson, and Dawn Song. 2011. Design
and evaluation of a real-time URL spam filtering service. In IEEE S & P
13. Quinlan, J. R. (1987). "Simplifying decision trees". International Journal of ManMachine Studies. 27 (3): 221–234. CiteSeerX 10.1.1.18.4267.
14. L. Breiman, "Random forests," Machine Learning, 2001.
15. T. Joachims, Learning to Classify Text Using Support Vector Machines: Methods,
Theory, and Algorithms. Boston: Kluwer Academic Publishers, 2002.
16. L. Breiman, "Random forests," Machine Learning, 2001.
17. Manuel Fern_andez Delgado, Eva Cernadas, Sen_en Barro, and Dinani Amorim,
"Do we Need Hundreds of Classifiers to Solve Real World Classification
Problems?," Journal of Machine Learning Research, vol. 15, pp. 3133-3181, 2014.
18. Lior Rokach and Oded Maimon, Data Mining and Knowledge Discovery
Handbook - Chapter 9 (Decision Trees), Oded Maimon and Lior Rokach, Eds.,
2005.
19. T. Joachims, Learning to Classify Text Using Support Vector Machines: Methods,
Theory, and Algorithms. Boston: Kluwer Academic Publishers, 2002