Journal of KIISE (정보과학회 논문지)

Korean Institute of Information Scientists and Engineers (한국정보과학회)
권호 표지
DOI QR코드

DOI QR Code

Spammer Detection using Features based on User Relationships in Twitter

관계 기반 특징을 이용한 트위터 스패머 탐지

  • 이찬식 (고양시자원봉사센터 고양시자원봉사홍보단) ;
  • 김준태 (동국대학교 컴퓨터공학과)
  • Received : 2014.05.13
  • Accepted : 2014.08.14
  • Published : 2014.10.15
⟨ Previous Next ⟩

Abstract

Twitter is one of the most famous SNS(Social Network Service) in the world. Twitter spammer accounts that are created easily by E-mail authentication deliver harmful content to twitter users. This paper presents a spammer detection method that utilizes features based on the relationship between users in twitter. Relationship-based features include friends relationship that represents user preferences and type relationship that represents similarity between users. We compared the performance of the proposed method and conventional spammer detection method on a dataset with 3% to 30% spammer ratio, and the experimental results show that proposed method outperformed conventional method in Naive Bayesian Classification and Decision Tree Learning.

트위터는 페이스북과 더불어 전 세계적으로 인기 있는 SNS(Social Network Service)이다. 트위터에서 이메일 인증 방식을 악용하여 대량 생성된 스패머 계정은 유해한 콘텐츠로 트위터 사용자들에게 불편함을 준다. 본 논문에서는 이러한 문제를 해결하고자 관계 기반 특징을 이용한 스패머 탐지 기법을 제안한다. 관계 기반 특징이란 사용자의 호감 정도를 표현할 수 있는 친구 관계 특징과 사용자 간의 유사성을 나타낼 수 있는 유형 관계 특징들을 의미한다. 기존의 스패머 탐지 기법과 본 논문에서 제안하는 탐지 기법의 성능을 스패머의 비율을 3%에서 30%까지 변화시키면서 비교 실험한 결과, 본 논문에서 제안하는 기법이 Naive Bayesian Classifier와 Decision Tree 모두에서 더 우수한 성능을 보였다.

Keywords

References

  1. K. Lee, J. Caverlee, S. Webb, "Uncovering Social Spammers: Social Honeypots +Machine Learning," The 33rd international ACM SIGIR conference on Research and development in information retrieval, pp. 435-442, 2010.
  2. C. Shekar, S. Wakade, K. J. Liszka, C. C. Chan, "Mining Pharmaceutical Spam from Twitter," The 10th International Conference on Intelligent Systems Design and Applications, pp. 813-817, 2010.
  3. F. Benevenuto, G. Magno, T. Rodrigues, V. Almeida, "Detecting Spammers on Twitter," Seventh annual Collaboration, Electronic messaging, Anti-Abuse and Spam Conference (CEAS), 2010.
  4. A. H. Wang, "Don't follow me: Spam detection in Twitter," The 5th International Conference on Security and Cryptography (SECRYPT), pp. 1-10, 2010.
  5. A. H. Wang, "Detecting Spam Bots in Online Social Networking Sites: A Machine Learning Approach," The 24th Annual IFIP WG 11.3 Working Conference on Data and Applications Security, pp. 335-342, 2010.
  6. J. Song, S. Lee, J. Kim, "Spam Filtering in Twitter using Sender-Receiver Relationship," The 14th International Symposium on Recent Advances in Intrusion Detection (RAID), pp. 301-317, 2011.
  7. K. Beck, "Analyzing Tweets to Identify Malicious Messages," IEEE International Conference on Electro/Information Technology (EIT), pp. 1-5, 2011.
  8. S. Yardi, D. Romero, G. Schoenebeck, d. boyd. (2010, January). First Monday (vol.15.) [Online]. Available: http://www.firstmonday.org (downloaded 2013, Apr. 11)
  9. D. Y. Won, K. J. Park, Y. J. Park, G. B. Shim, J. W. Lee, Y. H. Kim, "Spam Twit Filtering using NaIve Bayesian Algorithm and URL Analysis," Proc. of the 38th KIISE Fall Conference, Vol. 38, No. 2, pp.375-378, 2011. (in Korean)
  10. M. McCord, M. Chuah, "Spam Detection on Twitter Using Traditional Classifiers," The 8th international conference on Autonomic and trusted computing, 2011.
  11. D. Wang, D. Irani, C. Pu, "A Social-Spam Detection Framework," The 8th Annual Collaboration, Electronic messaging, Anti-Abuse and Spam Conference (CEAS), pp. 46-54, 2011.
  12. P. C. Lin, P. M. Huang, "A Study of Effective Features for Detecting Long-surviving Twitter Spam Accounts," Advanced Communication Technology (ICACT), pp. 841-846, 2013.
  13. S. H. Eom, W. Lee, J. H. Lee, "Specifying Spammers by Cycle Detection in Social Network," Proc. of the 39th KIISE Fall Conference, Vol. 39, No. 1, pp. 19-20, 2012. (in Korean)
  14. S. H. Eom, W. Lee, J. H. Lee, "Specifying Spammers by Cycle Detection in Social Network," Journal of KIISE : Computer Systems and Theory, Vol. 40, No. 1, pp. 24-29, Feb. 2013. (in Korean)
  15. A. A. Amleshwaram, N. Reddy, S. Yadav, G. Gu, C. Yang, "CATS: Characterizing Automation of Twitter Spammers," Communication Systems and Networks (COMSNETS), pp. 1-10, 2013.
  16. C. Yang, R. C. Harkreader, G. Gu, "Die Free or Live Hard? Empirical Evaluation and New Design for Fighting Evolving Twitter Spammers," In Recent Advances in Intrusion Detection (RAID), pp. 318-337, 2011.
  17. A. K. R, S, Kumar, "Twitter Spamming: Techniques And Defence Approaches," International Journal of Applied Engineering Research, Vol. 7, No. 11, 2012.
  18. K. Lee, J. Caverlee, K. Y. Kamath, Z. Cheng, "Detecting Collective Attention Spam," The 2nd Joint WICOW/AIRWeb Workshop on Web Quality, pp. 48-55, 2012.