Fake Accounts Detection on Twitter Using Blacklist

• Published in: 2018 IEEE ACIS 17th International Conference on Computer and Information Science (ICIS) pp. 562 - 566
• Main Authors: Swe, Myo Myo, Nyein Myo, Nyein
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2018
• Subjects: Blacklisting; Decorate; Feature extraction; keyword extraction approach; Support vector machines; topic modeling approach; Training; Twitter
• DOI: 10.1109/ICIS.2018.8466499

Social networking sites such as Twitter, Facebook, Weibo etc. are extremely mainstream today. Also, the greater part of the malicious users utilize these sites to persuade legitimate users for different purposes, for example, to promote their products item, to enter their spam links, to stigmatize other persons and so forth. An ever increasing number of users are utilized these social networking sites and fake accounts on these destinations are turned into a major issue. In this paper, fake accounts are detected using blacklist instead of traditional spam words list. Blacklist is created by using topic modeling approach and keyword extraction approach. We conduct an evaluation experiment with not only 1KS - 10KN dataset but also Social Honeypot dataset. The accuracy of the traditional spam words list based approach and our blacklist based approach are compared. Decorate, a meta-learner classifier is applied for classifying fake accounts on Twitter from legitimate accounts. Our approach achieves 95.4% accuracy and true positive rate is 0.95.