Deakin University
Browse

Asymmetric self-learning for tackling Twitter spam drift

Version 2 2024-06-06, 00:27
Version 1 2016-04-18, 11:22
conference contribution
posted on 2024-06-06, 00:27 authored by C Chen, J Zhang, Y Xiang, W Zhou
Spam has become a critical problem on Twitter. In order to stop spammers, security companies apply blacklisting services to filter spam links. However, over 90% victims will visit a new malicious link before it is blocked by blacklists. To eliminate the limitation of blacklists, researchers have proposed a number of statistical features based mechanisms, and applied machine learning techniques to detect Twitter spam. In our labelled large dataset, we observe that the statistical properties of spam tweets vary over time, and thus the performance of existing ML based classifiers are poor. This phenomenon is referred as 'Twitter Spam Drift'. In order to tackle this problem, we carry out deep analysis of 1 million spam tweets and 1 million non-spam tweets, and propose an asymmetric self-learning (ASL) approach. The proposed ASL can discover new information of changed tweeter spam and incorporate it into classifier training process. A number of experiments are performed to evaluate the ASL approach. The results show that the ASL approach can be used to significantly improve the spam detection accuracy of using traditional ML algorithms.

History

Volume

2015-August

Pagination

208-213

Location

Hong Kong

Start date

2015-04-26

End date

2015-05-01

ISSN

0743-166X

ISBN-13

9781467371315

Language

eng

Publication classification

E Conference publication, E1 Full written paper - refereed

Copyright notice

2015, IEEE

Title of proceedings

INFOCOM WKSHPS 2015: Proceedings of the Computer Communications Workshops

Event

IEEE Conference on Computer Communications Workshops (2015 : Hong Kong)

Publisher

IEEE

Place of publication

Piscataway, N.J.

Usage metrics

    Research Publications

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC