Detection of Twitter Spam's using Machine Learning Algorithm

International Journal of Computer Science and Engineering

© 2019 by SSRG - IJCSE Journal

Volume 6 Issue 3

Year of Publication : 2019

Authors : K. Jino Abisha, J.Roshan Nilofer, A.Silviya, Dr. S. Raja Ratna

10.14445/23488387/IJCSE-V6I3P103

How to Cite?

K. Jino Abisha, J.Roshan Nilofer, A.Silviya, Dr. S. Raja Ratna, "Detection of Twitter Spam's using Machine Learning Algorithm," SSRG International Journal of Computer Science and Engineering , vol. 6,  no. 3, pp. 10-13, 2019. Crossref, https://doi.org/10.14445/23488387/IJCSE-V6I3P103

Abstract:

With the increased popularity of online social networks, spammers find these platforms easily accessible to trap users in malicious activities by posting spam messages. In this work, Twitter platform is taken and spam tweets detection is performed. To stop spammers, semi supervised learning is used to detect spam tweets in twitter. Thus, industries and researchers have applied different approaches to make spam free social network platform. Some of them are only based on user-based features while others are based on tweet based features only. To solve this issue, a framework has been proposed which takes the user and tweet based features along with the tweet text feature to classify the tweets. The benefit of using tweet text feature is that the spam tweets can be identified even if the spammer creates a new account which was not possible only with the user and tweet based features. The work has been evaluated with three different machine learning algorithms namely - Support Vector Machine, Neural Network, Random Forest. With Naive Bayes classifier, about 80% of accuracy is obtained.

Keywords:

Twitter, spam, supervised learning, support vector.

References:

[1] Dorri. A., Abadi, M., and Dadfarnia, M. (2018), “Social Bot Hunter: Botnet Detection in Twitter-Like Social Networking Services Using Semi-Supervised Collective Classification”, IEEE 16th International Conference on Dependable, Autonomic and Secure Computing, 2018.
[2] Erwin B. Setiawan, Dwi H. Widyantoro, and Kridanto Surendro, ”Detecting Indonesian Spammer on Twitter”, School of Electrical Engineering and Informatics, No 10, 2018.
[3] Li, W., Gao, M., Rong, W., Wen, J., Xiong, Q., and Ling, B, “Lssl-ssd: Social spammer detection with laplacian score and semi-supervised learning” International Conference on Knowledge Science, Engineering and Management (pp. 439-450), 2016.
[4] M. Boyd and N. B. Ellison, “Social network sites: Definition, history, and scholarship,” Journal of Computer Mediat. Communication, vol. 13, no. 1, pp. 210– 230, Oct. 2007.
[5] H. Nguyen, “state of social media spam”, Nexgate, Research Report, 2013.
[6] Z. Chu, I. Widjaja, and H. Wang, “Detecting social spam campaigns on Twitter,” ACNS 2012.
[7] J. Zhang, R. Zhang, Y. Zhang, and G. Yan, “The rise of social botnets: Attacks and countermeasures,” IEEE Transaction on Dependable Secure Computation.
[8] S. Cresci, R. Di Pietro, M. Petrocchi, A. Spognardi, and M. Tesconi, “The paradigm-shift of social spam bots: Evidence, theories and tools for the arms race,” Proceedings in. 26th International Conference on World Wide Web Companion, Apr. 2017, pp. 963–972.
[9] S. Lee and J. Kim, “Warning bird: A near real-time detection system for suspicious URLs in twitter stream”, IEEE Transaction Dependable Security Comput., vol. 10, pp. 183–195, 2013.
[10] Vishwarupe, M. Bedekar, M. Pande, and A. Hiwale, “Intelligent Twitter Spam Detection : A Hybrid Approach,” Smart Trends System Security, ,” Proceedings in. 26th International Conference on World Wide Web Companion, pp. 189–197, 2017.
[11] Verma, M., and Sofat, “Techniques to detect spammers in twitter-a survey”, International Journal of Computer Applications, 2014.
[12] He, H., Watson, T., Maple, C., Mehnen, J., and Tiwari, A, ”A new semantic attribute deep learning with a linguistic attribute hierarchy for spam detection” IEEE International Joint Conference on Neural Networks, pp. 3862-3869, 2017.
[13] C. Grier, K. Thomas, V. Paxson, and M. Zhang, “@ spam : The Underground on 140 Characters or Less Categories and Subject Descriptors,” Proceedings in 17th ACM Conf. Computation, Communication and Security, pp. 27– 37, 2010.
[14] J.Martinez-romo and L. Araujo, “Expert Systems with Applications Detecting malicious tweets in trending topics using a statistical analysis of language,” Expert System Application, vol. 40, no. 8, pp. 2992–3000, 2013.
[15] A. H. Wang, “Don‟t follow me: Spam detection in Twitter,” Proceedings in International Conference in Security and Cryptography, vol. 2010, pp. 1–10, 2010