Prediksi Akun Bot pada Media Sosial X Menggunakan Random Forest, XGBoost, dan SVM
DOI:
https://doi.org/10.24002/jiaj.v6i2.12948Keywords:
bot, x, machine learning, hyperparameter tuningAbstract
The social media platform X is often misused, one example being the creation of fake accounts operated by bots. To address this issue, various machine learning models have been developed to detect bot accounts, particularly Random Forest, XGBoost, and Support Vector Machine (SVM). This study aims to compare the performance of these three models in predicting bot accounts on social media platform X and to determine the best model based on the f1-score. In addition, this research applies three hyperparameter tuning methods, namely grid search, random search, and Bayesian optimization. The results show that the XGBoost model with Bayesian optimization achieves the best performance. However, its performance decreases when applied to imbalanced datasets.
Penggunaan media sosial X seringkali disalahgunakan, salah satunya dengan membuat akun palsu yang dijalankan oleh bot. Saat ini, telah banyak dikembangkan sistem untuk mendeteksi akun bot pada media sosial X dengan memanfaatkan model machine learning, khususnya algoritma Random Forest, XGBoost, dan SVM. Penelitian ini bertujuan untuk membandingkan performa dari ketiga model tersebut dalam memprediksi akun bot pada media sosial X dan menentukan model terbaik berdasarkan nilai f1-score. Pada penelitian ini juga dikembangkan penggunaan hyperparameter tuning grid search, random search, dan Bayesian optimization. Hasil penelitian ini menunjukkan bahwa model terbaik untuk prediksi akun bot pada media sosial X adalah XGBoost dengan hyperparameter tuning Bayesian optimization. Namun, model ini mengalami penurunan performa ketika digunakan untuk memprediksi akun bot pada data yang tidak seimbang.
References
[1] A, Dehghan, K. Siuta, A. Skorupka, A. Dubey, A. Betlen, D. Miller, W. Xu, B. Kamiński, P. Prałat, “Detecting bots in social-networks using node and structural embeddings,” J Big Data, vol. 10, no. 1, Des 2023, doi: 10.1186/s40537-023-00796-3.
[2] J. Giroux, G. Ariyarathne, A. C. Nwala, C. Fanelli, “Unmasking social bots: how confident are we?,” EPJ Data Sci, vol. 14, no. 1, Des 2025, doi: 10.1140/epjds/s13688-025-00536-y.
[3] M. Aljabri, R. Zagrouba, A. Shaahid, F. Alnasser, A. Saleh, D. M. Alomari, “Machine learning-based social media bot detection: a comprehensive literature review,” Soc Netw Anal Min, vol. 13, no. 1, Des 2023, doi: 10.1007/s13278-022-01020-5.
[4] W. Dracewicz & M. Sepczuk, “Detecting Fake Accounts on Social Media Portals—The X Portal Case Study,” Electronics (Switzerland), vol. 13, no. 13, Jul 2024, doi: 10.3390/electronics13132542.
[5] H. Kurniawan, “Deteksi Twitter Bot Menggunakan Klasifikasi Decision Tree,” Jurnal Sustainable: Jurnal Hasil Penelitian dan Industri Terapan, vol. 09, no. 01, hlm. 31–37, 2020.
[6] D. M. Siddiqa & D. W. Albert, “Detecting Malicious Twitter Bots Using Machine Learning”, International Journal of Information Technology and Computer Engineering, 12 (3), doi: 10.62647/ijitce.2024.v12.i3.pp40-44.
[7] S. Gurajala, J. S. White, B. Hudson, B. R. Voter, dan J. N. Matthews, “Profile Characteristics of Fake Twitter Accounts,” Big Data Soc, vol. 3, no. 2, Des 2016, doi: 10.1177/2053951716674236.
[8] A. Ramalingaiah, S. Hussaini, dan S. Chaudhari, “Twitter Bot Detection Using Supervised Machine Learning,” Journal of Physics: Conference Series, IOP Publishing Ltd, Agu 2021. doi: 10.1088/1742-6596/1950/1/012006.
[9] J. Luo dan C. Jin, “Fusing Content and Social Relationships: A Multi-Modal Heterogeneous Graph Transformer Approach For Social Bot Detection,” EPJ Data Sci, vol. 14, no. 1, Des 2025, doi: 10.1140/epjds/s13688-025-00583-5.
[10] N. Jalal dan K. Z. Ghafoor, “Machine Learning Algorithms for Detecting and Analyzing Social Bots Using a Novel Dataset,” ARO-The Scientific Journal of Koya University, vol. 10, no. 2, hlm. 11–21, Des 2022, doi: 10.14500/aro.11032.
[11] A. A. Zahra, W. Widyawan & S. Fauziati, “Development of Bot Detection Applications on Twitter Social Media Using Machine Learning with a Random Forest Classifier Algorithm,” IJITEE (International Journal of Information Technology and Electrical Engineering), 4(2), 66-73, 2020.
[12] O. Arranz-Escudero, L. Quijano-Sanchez, dan F. Liberatore, “Enhancing misinformation countermeasures: a multimodal approach to twitter bot detection,” Soc Netw Anal Min, vol. 15, no. 1, Des 2025, doi: 10.1007/s13278-025-01435-w.
[13] R. G. Al-Azawi dan S. O. Al-Mamory, “Unsupervised Machine Learning for Bot Detection on Twitter: Generating and Selecting Features for Accurate Clustering,” Inteligencia Artificial, vol. 27, no. 73, hlm. 142–158, Jun 2024, doi: 10.4114/intartif.vol27iss73pp142-158.
[14] F. K. Alarfaj, H. Ahmad, H. U. Khan, A. M. Alomair, N. Almusallam, dan M. Ahmed, “Twitter Bot Detection Using Diverse Content Features and Applying Machine Learning Algorithms,” Sustainability (Switzerland), vol. 15, no. 8, Apr 2023, doi: 10.3390/su15086662.
[15] L. Li, O. Vásárhelyi, dan B. Vedres, “Social bots spoil activist sentiment without eroding engagement,” Sci Rep, vol. 14, no. 1, Des 2024, doi: 10.1038/s41598-024-74032-0.
[16] M. Kolomeets, O. Tushkanova, V. Desnitsky, L. Vitkova, dan A. Chechulin, “Experimental Evaluation: Can Humans Recognise Social Media Bots?,” Big Data and Cognitive Computing, vol. 8, no. 3, Mar 2024, doi: 10.3390/bdcc8030024.
[17] R. Kenny, B. Fischhoff, A. Davis, dan C. Canfield, “Improving Social Bot Detection Through Aid and Training,” Hum Factors, vol. 66, no. 10, hlm. 2323–2344, Okt 2024, doi: 10.1177/00187208231210145.
[18] A. A. Darem, A. A. Alhashmi, M. H. Alanazi, A. F. Alanezi, Y. Said, L. A. Darem, M. M. Hussain, “Cybersecurity in social networks: An ensemble model for Twitter bot detection,” International Journal of Advanced and Applied Sciences, vol. 11, no. 11, hlm. 130–141, Nov 2024, doi: 10.21833/ijaas.2024.11.014.
[19] A. Shevtsov, C. Tzagkarakis, D. Antonakaki, dan S. Ioannidis, “Identification of Twitter Bots Based on an Explainable Machine Learning Framework: The US 2020 Elections Case Study,” AAAI Conference on Artificial Intelligence, 2022. [Daring]. Tersedia pada: www.aaai.org
[20] R. Shukla, A. Sinha, dan A. Chaudhary, “TweezBot: An AI-Driven Online Media Bot Identification Algorithm for Twitter Social Networks,” Electronics (Switzerland), vol. 11, no. 5, Mar 2022, doi: 10.3390/electronics11050743.
[21] E. Alothali, K. Hayawi, dan H. Alashwal, “Hybrid feature selection approach to identify optimal features of profile metadata to detect social bots in Twitter,” Soc Netw Anal Min, vol. 11, no. 1, Des 2021, doi: 10.1007/s13278-021-00786-4.
[22] M. Heidari, J. H. Jones, dan O. Uzuner, “Deep Contextualized Word Embedding for Text-based Online User Profiling to Detect Social Bots on Twitter,” dalam IEEE International Conference on Data Mining Workshops, ICDMW, IEEE Computer Society, Nov 2020, hlm. 480–487. doi: 10.1109/ICDMW51313.2020.00071.
[23] S. Cresci, A. Spognardi, M. Petrocchi, M. Tesconi, dan R. Di Pietro, “The paradigm-shift of social spambots: Evidence, theories, and tools for the arms race,” dalam 26th International World Wide Web Conference 2017, WWW 2017 Companion, International World Wide Web Conferences Steering Committee, 2017, hlm. 963–972. doi: 10.1145/3041021.3055135.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Copyright of this journal is assigned to Jurnal Informatika Atma Jogja as the journal publisher by the knowledge of author, whilst the moral right of the publication belongs to author. Every printed and electronic publications are open access for educational purposes, research, and library. The editorial board is not responsible for copyright violation to the other than them aims mentioned before. The reproduction of any part of this journal (printed or online) will be allowed only with a written permission from Jurnal Informatika Atma Jogja .
