SavedAdd your journal

Journals / Dicle Üniversitesi Mühendislik Fakültesi Mühendislik Dergisi / 2026 / Cilt: 17 Sayı: 2

Uncovering coin market manipulation on X using machine learning

Makine öğrenmesi kullanarak X üzerinde kripto para piyasası manipülasyonunun ortaya çıkarılması

Zehra Nur Özbay(EGE UNIVERSITY, INTERNATIONAL INSTITUTE OF COMPUTER)0000-0001-5680-1227
Aybars Uğur(EGE UNIVERSITY, FACULTY OF ENGINEERING, DEPARTMENT OF COMPUTER ENGINEERING)0000-0003-3622-7672
Mehmet Emin Dalkılıç(EGE UNIVERSITY, INTERNATIONAL INSTITUTE OF COMPUTER)0000-0003-3932-5155
Pages
—
Publication Date
2026-06-25
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

The cross-validated accuracy of SVM is further improved through hyperparameter tuning, resulting in 99.70%.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Spam-bots have become a widespread problem due to the ease of creating accounts on the X platform.
📊
Key Findings & Data:These bots are designed to automatically generate and disseminate unsolicited content, frequently for advertising purposes or events of questionable legality.
💡
Conclusion & Impact:The cross-validated accuracy of SVM is further improved through hyperparameter tuning, resulting in 99.70%.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:sosyal medya · spam · kripto para

Abstract

Spam-bots have become a widespread problem due to the ease of creating accounts on the X platform. These bots are designed to automatically generate and disseminate unsolicited content, frequently for advertising purposes or events of questionable legality. A key challenge in detecting these spam-bots is their ability to create accounts rapidly, post certain volumes of content around an event, and then become dormant. This study examines spam-bot accounts created to promote cryptocurrency trading on X. We present a novel approach to obtain a spam-bot dataset for coin-related tweets, including data collection, analysis, and labeling. For data preprocessing, we applied Natural Language Processing techniques, which resulted in an imbalanced dataset. We used BERT embeddings for feature extraction and evaluated the performance of nine machine learning algorithms in detecting the tweets of spam-bot accounts. The SVM model achieves the highest cross-validated accuracy of 98.09% on the balanced dataset, produced using the SMOTE oversampling technique. On the original imbalanced dataset, Logistic Regression has the highest accuracy at 96.46%. The cross-validated accuracy of SVM is further improved through hyperparameter tuning, resulting in 99.70%.

Özet

X platformunda hesap açmanın kolaylığı nedeniyle spam-botlar yaygın bir sorun haline gelmiştir. Bu botlar, genellikle reklam amaçlı veya yasal açıdan şüpheli etkinlikler için, istenmeyen içerikleri otomatik olarak üretmek ve yaymak üzere tasarlanmıştır. Bu spam botlarını tespit etmede karşılaşılan en önemli zorluk, hızlı bir şekilde hesap oluşturabilmeleri, bir etkinlik etrafında belirli hacimlerde içerik yayınlamaları ve ardından pasif duruma geçmeleridir. Bu çalışma, X üzerinde kripto para ticaretini teşvik etmek için oluşturulan spam-bot hesaplarını incelemektedir. Çalışmada kripto para ile ilgili tweet’ler için veri toplama, analiz ve etiketleme süreçlerini içeren özgün bir spam-bot veri kümesi elde etme yaklaşımı sunulmuştur. Veri ön işleme için Doğal Dil İşleme teknikleri uygulanmış ve bu da dengesiz bir veri kümesiyle sonuçlanmıştır. Özellik çıkarımı için BERT yerleştirmeleri kullanılmış ve spam-bot hesaplarının tweet’lerini tespit etmede dokuz makine öğrenmesi algoritmasının performansı değerlendirilmiştir. Buna göre, SVM modeli SMOTE aşırı örnekleme tekniği kullanılarak üretilen dengeli veri kümesinde %98,09'luk en yüksek çapraz doğrulama doğruluğunu elde etmiştir. Orijinal dengesiz veri kümesinde ise %96,46 doğrulukla en yüksek başarıyı Lojistik Regresyon göstermiştir. SVM’nin çapraz doğrulanmış doğruluğu, hiperparametre ayarlamalarıyla daha da geliştirilmiş ve %99,70’e ulaşmıştır.

🔖

Cite This Article

Özbay, Z. N., Uğur, A., Dalkılıç, M. E. (2026). Uncovering coin market manipulation on X using machine learning. Dicle Üniversitesi Mühendislik Fakültesi Mühendislik Dergisi, Cilt: 17 Sayı: 2. https://doi.org/10.24012/dumf.1789337

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (16)

  1. E. H. Tusher, M. A. Ismail, M. A. Rahman, A. H. Alenezi, and M. Uddin, "Email Spam: A Comprehensive Review of Optimize Detection Methods, Challenges, and Open Research Problems," IEEE Access, vol. 12, pp. 143627–143657, 2024, doi: 10.1109/ACCESS.2024.3467996.
  2. L. Cong, X. Li, K. Tang, and Y. Yang, "Crypto Wash Trading", SSRN Journal, 2019, doi: 10.2139/ssrn.3530220.
  3. P. Manasa et al., "Tweet Spam Detection Using Machine Learning and Swarm Optimization Techniques", IEEE Transactions on Computational Social Systems, vol. 11, no. 4, pp. 4870–4877, Aug. 2024, doi: 10.1109/TCSS.2022.3230823.
  4. S. Bazzaz Abkenar, M. Haghi Kashani, M. Akbari, and E. Mahdipour, "Learning textual features for Twitter spam detection: A systematic literature review", Expert Systems with Applications, vol. 228, p. 120366, Oct. 2023, doi: 10.1016/j.eswa.2023.120366.
  5. M. Chakraborty, S. Das, and R. Mamidi, "Detection of Fake Users in SMPs Using NLP and Graph Embeddings", in 2022 14th International Conference on COMmunication Systems & NETworkS (COMSNETS), Jan. 2022, pp. 754–758. doi: 10.1109/COMSNETS53615.2022.9668371.
  6. M. Heidari, J. H. J. Jones, and O. Uzuner, "An Empirical Study of Machine learning Algorithms for Social Media Bot Detection", in 2021 IEEE International IOT, Electronics and Mechatronics Conference (IEMTRONICS), Apr. 2021, pp. 1–5. doi: 10.1109/IEMTRONICS52119.2021.9422605.
  7. O. Çıtlak, M. Dörterler, and İ. Dogru, "A Hybrid Spam Detection Framework for Social Networks," Politeknik Dergisi, vol. 26, no. 2, pp. 823–837, Jul. 2023, doi: 10.2339/politeknik.933785.
  8. M. Sumathi and S. P. Raja, "Machine learning algorithm-based spam detection in social networks," Soc. Netw. Anal. Min., vol. 13, no. 1, p.104, Aug. 2023, doi: 10.1007/s13278-023-01108-6.
  9. Y. Li, Y. Xiao, Y. Huang, and R. Ma, “Analysis of social networks content to identify fake news using stacked combination of deep neural networks,” Egyptian Informatics Journal, vol. 30, p. 100707, Jun. 2025, doi: 10.1016/j.eij.2025.100707.
  10. V. Vysotska, N. Babkova, D. Huliieva, Z. Kochuieva, N. Ugolnikova, and M. Kozulia, Identifying fake news in political discourse behavior using machine learning methods. 2025. doi: 10.31110/COLINS/2025-3/012.
  11. A. A. Alhaj, O. Safwat, Y. Ghoneim, I. Zualkernan, and A. R. Sajun, “Investigating Fake News Detection Using BERT/RoBERTa LLMs,” in Proceedings of Tenth International Congress on Information and Communication Technology, X.-S. Yang, R. S. Sherratt, N. Dey, and A. Joshi, Eds., Singapore: Springer Nature, 2025, pp. 241–251. doi: 10.1007/978-981-96-6929-5_19.
  12. E.-S. Apostol, C.-O. Truică, and A. Paschke, “ContCommRTD: A Distributed Content-Based Misinformation-Aware Community Detection System for Real-Time Disaster Reporting,” IEEE Transactions on Knowledge and Data Engineering, vol. 36, no. 11, pp. 5811–5822, Nov. 2024, doi: 10.1109/TKDE.2024.3417232.
  13. J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding,” May 24, 2019, arXiv: arXiv:1810.04805. doi: 10.48550/arXiv.1810.04805.
  14. M. Q. Alnabhan and P. Branco, “Fake News Detection Using Deep Learning: A Systematic Literature Review,” IEEE Access, vol. 12, pp. 114435–114459, 2024, doi: 10.1109/ACCESS.2024.3435497. [15] “Where’s the ‘X’ Factor? X (Twitter) One Year Post-Acquisition Recap,” Sensor Tower Blog. Accessed on: Sept. 22, 2025, [Online] Available: https://sensortower.com/blog/wheres-the-x-factor-x-twitter-one-year-post-acquisition-recap.
  15. I. Inuwa-Dutse, M. Liptrott, and I. Korkontzelos, "Detection of spam-posting accounts on Twitter", Neurocomputing, vol. 315, pp. 496–511, Nov. 2018, doi: 10.1016/j.neucom.2018.07.044.
  16. European Commission, Ed., A multi-dimensional approach to disinformation: report of the independent High level Group on fake news and online disinformation. Luxembourg: Publications Office, 2018. doi: 10.2759/0156.