A Deep Learning-Based Approach for Bot Detection in Trending Hashtags on X

Authors

• Mehboob Hussain, Department of Robotics & Artificial Intelligence, University is Shaheed Zulfikar Ali Bhutto Institute of Science and Technology, Islamabad 44090, Pakistan
• Muhammad Rizwan Rashid Rana, Department of Robotics & Artificial Intelligence, University is Shaheed Zulfikar Ali Bhutto Institute of Science and Technology, Islamabad 44090, PakistanFollow
• Muhammad Imran, Department of Robotics & Artificial Intelligence, University is Shaheed Zulfikar Ali Bhutto Institute of Science and Technology, Islamabad 44090, Pakistan
• Muhammad Shoaib, Department of Robotics & Artificial Intelligence, University is Shaheed Zulfikar Ali Bhutto Institute of Science and Technology, Islamabad 44090, Pakistan
• Muhammad Hasaan Mujtaba, Department of Robotics & Artificial Intelligence, University is Shaheed Zulfikar Ali Bhutto Institute of Science and Technology, Islamabad 44090, Pakistan

Abstract

The widespread presence of bots on social media platforms, such as X (formerly Twitter), poses a significant threat to the integrity of online information by facilitating the dissemination of misinformation and manipulating public discourse. This study proposes a robust deep learning-based framework, DeepBot, to detect bot participation in trending hashtags and discussions on X. The approach uses a dataset sourced from Kaggle, comprising user profile metadata, including follower count, tweet frequency, account verification status, and engagement metrics. The data were subjected to comprehensive preprocessing, including noise removal, part-of-speech (POS) tagging, and word embedding using the pre-trained GloVe model. RoBERTa is employed for feature extraction to capture deep contextual semantics, followed by classification through a deep neural network (DNN) to effectively distinguish between human users and bots. The proposed model is evaluated against established baselines using standard performance metrics. Experimental results demonstrate that DeepBot achieves superior performance with an accuracy of 92.82%, precision of 91.24%, and recall of 91.78%, confirming its effectiveness in enhancing the reliability of bot detection in social media trend analysis.

References

1. Z. Jiang, W. Chen, W. Zhang, S. Zhang, J. Chen, H. Wan, Acta Sci. Nat. Univ. Pekin. 61/4 (2025) 639.
2. J.M. Berger, J. Morgan, The ISIS Twitter census: Defining and describing the population of ISIS supporters on Twitter, The Brookings Institution, https://www.brookings.edu/articles/the-isis-twitter census-defining-and-describing-the-population-of isis-supporters-on-twitter/, 2015.
3. Z. Chu, S. Gianvecchio, H. Wang, S. Jajodia, IEEE Trans. Dependable Secure Comput. 9/6 (2012) 811.
4. W. Arroyo-Machado, E. Herrera-Viedma, and D. Torres-Salinas, J. Assoc. Inf. Sci. Technol. 76/8 (2025) 1105.
5. G. Lingam, S.K. Das, Knowl.Based Syst. 311 (2025) 113019.
6. S. Cresci, R. Di Pietro, M. Petrocchi, A. Spognardi, M. Tesconi, Proceedings of the 26th International Conference on World Wide Web Companion, Perth, Australia, 2017, p.963.
7. S. Shi, K. Qiao, Z. Liu, J. Yang, C. Chen, J. Chen, et al., Neurocomputing 647 (2025) 130490.
8. S. Cresci, M. Petrocchi, A. Spognardi, S. Tognazzi, Companion Proc. Web Conf. (2018) 1469.
9. C.A. Davis, O. Varol, E. Ferrara, A. Flammini, F. Menczer, Proc. 25th Int. Conf. Companion World Wide Web. (2016) 273.
10. L. Luceri, A. Deb, A. Badawy, E. Ferrara, Companion Proceedings of The 2019 World Wide Web Confe rence (WWW '19). Association for Computing Mac hinery, New York, USA, 2019, p.1007.
11. C. Özkurt, Chaos Fractals 1/1 (2024) 19.
12. P. Rakshit, A. Sarkar, Multimeda Tools Appl. 84/2 (2025) 979.
13. C. Monica, N. Nagarathna, SN Comput. Sci. 1/2 (2020) 89.
14. T. Wang, Z. Wang, H. Li, C. Xia, and C. Zhao, IEEE Trans. Comput. Social Syst. 12/5 (2025) 3416.
15. D. Martín-Gutiérrez, G. Hernández-Peñaloza, A.B. Hernández, A. Lozano-Diez, F. Álvarez, IEEE Access. 9 (2021) 54591.
16. F.K. Alarfaj, H. Ahmad, H.U. Khan, A.M. Alomair, N. Almusallam, M. Ahmed, Sustainability. 15/8 (2023) 6662.
17. Z. Zeng, T. Li, S. Sun, J. Sun, and J. Yin, Data Technol. Appl. 56/3 (2022) 409.
18. A. Anwar, H. Ilyas, U. Yaqub, S. Zaman, Proceedings of the 22nd Annual International Conference on Digital Government Research (dg.o '21). Association for Computing Machinery, New York, USA, 2021, 82.
19. S. Mohammad, M.U.S. Khan, M. Ali, L. Liu, M. Shardlow, R. Nawaz, 2019 Third World Conference on Smart Trends in Systems Security and Sustai nablity (WorldS4), London, UK, 2019, p.215.
20. J. Pastor-Galindo, F.G. Mármol, G.M. Pérez, Inf. Sci. 613 (2022) 161.
21. G. Vyas, P. Vyas, P. Muzumdar, A. Chennamaneni, A. Rajavat, R. Rawat, Convers. Artif. Intell. (2024) 71.
22. A. Albladi, M. Islam, C. Seals, IEEE Access. 13 (2025) 30444. 1
23. S. Chopra, P. Agarwal, J. Ahmed, S.S. Biswas, A.J. Obaid, SN Comput. Sci. 5 (2024) 889.
24. W. Bai, X. Ye, Y. Xie, S. Van Zandt, X. Huang, D. Sengupta, Ann. Am. Assoc. Geogr. 116/1 (2026) 140–159.
25. H. Cheng, M. Zhang, J.Q. Shi, IEEE Trans. Pattern Anal. Mach. Intell. 46/12 (2024) 10558.
26. X. Wang, K. Wang, K. Chen, Z. Wang, K. Zheng, Knowledge-Based Syst. 293 (2024) 111690.
27. M. Bibi, Z.H. Qaisar, N. Aslam, M. Faheem, P. Akhtar, Eng. Rep. 6/9 (2024) e12838.
28. V. B. Nambiar, B. Ramamurthy, P. Veeresha, Int. J. Math. Comput. Eng. 2/1 (2023) 59.
29. M.N. Raihen, S. Akter, Int. J. Math. Comput. Eng. 2/1 (2024) 1.

Recommended Citation

Hussain, Mehboob; Rana, Muhammad Rizwan Rashid; Imran, Muhammad; Shoaib, Muhammad; and Mujtaba, Muhammad Hasaan (2026) "A Deep Learning-Based Approach for Bot Detection in Trending Hashtags on X," Makara Journal of Technology: Vol. 30: Iss. 1, Article 4.
DOI: 10.7454/mst.v30i1.1733
Available at: https://scholarhub.ui.ac.id/mjt/vol30/iss1/4