A Review of Hybrid Machine Learning Approaches for Fraud Detection in Online Social Networks

References

[1] Varol, O., Ferrara, E., Davis, C., Menczer, F., & Flammini, F. (2017). Online human-bot interactions: Detection, estimation, and characterization. Proceedings of the International AAAI Conference on Web and Social Media, 11(1), 280–289. Crossref

[2] Benevenuto, F., Rodrigues, T., Almeida, V., Almeida, J., & Gonçalves, M. (2010). Detecting spammers on Twitter. Proceedings of the Collaboration, Electronic Messaging, Anti-Abuse and Spam Conference (CEAS’10).

[3] Yang, Z., Wilson, C., Wang, X., Gao, T., Zhao, B. Y., & Dai, Y. (2014). Uncovering social network sybils in the wild. ACM Transactions on Knowledge Discovery from Data, 8(1). Crossref

[4] Cresci, S., Di Pietro, R., Petrocchi, M., Spognardi, A., & Tesconi, M. (2017). The paradigm shift in social bot research. Communications of the ACM, 61(3), 72–80.

[5] Wang, G., Mohanlal, M., Wilson, C., Wang, X., Metzger, M., Zheng, H., & Zhao, B. (2013). Social Turing tests: Crowdsourcing sybil detection. Proceedings of the 20th Network and Distributed System Security Symposium (NDSS).

[6] Stringhini, G., Wang, G., Egele, M., Kermarrec, A., Kruegel, C., Vigna, G., & Zhang, H. (2015). Follow the money: Distinguishing regular and fraudulent accounts in online social networks. NDSS.

[7] Lee, K., Eoff, B., & Caverlee, J. (2011). Seven months with the devils: A long-term study of content polluters on Twitter. Proceedings of the International AAAI Conference on Web and Social Media, 5(1), 185–192. Crossref

[8] Ahmed, F., & Abulaish, M. (2013). A generic statistical approach for spam detection in Online Social Networks. Computer Communications, 36(10–11), 1120–1129. Crossref

[9] Ferrara, E., Varol, O., Davis, C., Menczer, F., & Flammini, F. (2016). The rise of social bots. Communications of the ACM, 59(7), 96–104. Crossref

[10] Almaatouq, A., Alsaleh, M., Alarifi, A., Al- Salman, A., & Al-Khalifa, H. (2016). Semantic-graph based approach for efficient spam detection in online social networks. IEEE Access, 4, 9400–9412. Crossref

@article{1723102,
      author = {Dr. Usha Rani},
      title = {A Review of Hybrid Machine Learning Approaches for Fraud Detection in Online Social Networks},
      journal = {Iconic Research And Engineering Journals},
      year = {2020},
      volume = {4},
      number = {2},
      pages = {461-463},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1723102.pdf},
      abstract = {Online social networks (OSNs) have become an essential platform for human communication, business and public expression, however the popularity of these OSNs has given rise to large-scale abuse by way of fraud, identity deception, spamming and digital manipulation. It is difficult to detect this misuse since the fraudulent accounts are designed as legitimate users. Hybrid machine learning methods that integrate several analysis methodologies (versus using a single method) have been proposed and demonstrated as a potentially effective solution.In this paper, we summarize hybrid Machine Learning techniques for OSN fraud detection in terms of their architectures, effectiveness and limitations. The survey also focuses on important frontiers in feature engineering, graph-based learning, and ensemble learning, and ends with some research gaps that are still open till today. It further underlines the increasing demand for scalable models to cope with real-time detection over large-scale social media.},
      keywords = {OSN, Machine Learning, Ensemble Learning, Scalable models, Spamming.},
      month = {August},
  }