A Hybrid Ensemble Learning Approach for Detecting Bots on Twitter

doi:10.23940/ijpe.24.10.p3.610620

Abstract

Abstract:

The proliferation of social media platforms has revolutionized communication, but it has also given rise to social media bots that spread misinformation, manipulate public opinion, and compromise online discourse integrity. This study addresses the critical issue of detecting social media bots on Twitter, where traditional detection methods often fall short due to the evolving nature of these bots and the vast amount of data involved. To overcome these challenges, this research proposes a hybrid ensemble model that combines feature engineering and natural language processing techniques. The ensemble model is a meta-model that predicts the nature of a Twitter account based on the outputs of two base models. The first model uses a combination of engineered profile and content-based features, while the second model employs automatically extracted natural language processing features from posted tweets. By integrating these distinct features, the hybrid model captures a broader spectrum of bot behaviors and characteristics, leading to more accurate and robust detection. This combined approach allows the meta-model to identify bots that might evade detection when only one type of feature is used, offering a more holistic understanding of bot behavior across both structural and content dimensions. Extensive experiments demonstrate significant improvements in detection performance, achieving an impressive F1-score of 90.22% on the challenging Twibot-20 dataset, outperforming state-of-the-art models.

Key words: social media, bot detection, twitter, hybrid approach, ensemble learning, natural language processing

Hannousse Abdelhakim and Talha Zied. A Hybrid Ensemble Learning Approach for Detecting Bots on Twitter [J]. Int J Performability Eng, 2024, 20(10): 610-620.

Add to citation manager EndNote|Reference Manager|ProCite|BibTeX|RefWorks

References 22

[1]	Kaplan, A.M. and Haenlein, M. , 2010. Users of the world, unite! The challenges and opportunities of Social Media. Business horizons, 53( 1), pp. 59- 68.
[2]	Mangold, W.G. and Faulds, D.J. , 2009. Social media: The new hybrid element of the promotion mix. Business horizons, 52( 4), pp. 357- 365.
[3]	Freelon, D. , McIlwain, C.D. and Clark, M. , 2016. Beyond the hashtags:# Ferguson,# Blacklivesmatter, and the online struggle for offline justice. Center for Media & Social Impact, American University, Forthcoming.
[4]	Aljabri, M. , Zagrouba, R. , Shaahid, A. , Alnasser, F. , Saleh, A . and Alomari, D.M. , 2023. Machine learning-based social media bot detection: a comprehensive literature review. Social Network Analysis and Mining, 13( 1), p. 20.
[5]	Cresci, S. , Di Pietro, R. , Petrocchi, M. , Spognardi, A . and Tesconi, M. , 2017, April. The paradigm-shift of social spambots: Evidence, theories, and tools for the arms race. In Proceedings of the 26th international conference on world wide web companion (pp. 963- 972).
[6]	Shafahi, M. , Kempers, L . and Afsarmanesh, H. , 2016, December. Phishing through social bots on Twitter. In 2016 IEEE international conference on big data (big data) (pp . 3703- 3712). IEEE.
[7]	Shao, C. , Ciampaglia, G.L. , Varol, O. , Yang, K.C. , Flammini, A . and Menczer, F. , 2018. The spread of low-credibility content by social bots. Nature communications, 9( 1), pp. 1- 9.
[8]	Hayawi, K. , Saha, S. , Masud, M.M. , Mathew, S.S. and Kaosar, M. , 2023. Social media bot detection with deep learning methods: a systematic review. Neural Computing and Applications, 35( 12), pp. 8903- 8918.
[9]	Orabi, M. , Mouheb, D. , Al Aghbari, Z . and Kamel, I. , 2020. Detection of bots in social media: a systematic review. Information Processing & Management, 57( 4), p. 102250.
[10]	Cresci, S. , Di Pietro, R. , Petrocchi, M. , Spognardi, A . and Tesconi, M. , 2015. Fame for sale: Efficient detection of fake Twitter followers. Decision Support Systems, 80, pp. 56- 71.
[11]	Abreu, J.V.F. , Ralha, C.G. and Gondim, J.J.C. , 2020, November. Twitter bot detection with reduced feature set. In 2020 IEEE International Conference on Intelligence and Security Informatics (ISI) (pp . 1- 6). IEEE.
[12]	Yang, K.C. , Varol, O. , Hui, P.M. and Menczer, F. , 2020, April. Scalable and generalizable social bot detection through data selection. In Proceedings of the AAAI conference on artificial intelligence (Vol . 34, No. 01, pp. 1096- 1103).
[13]	Alarfaj, F.K. , Ahmad, H. , Khan, H.U. , Alomair, A.M. , Almusallam, N . and Ahmed, M. , 2023. Twitter bot detection using diverse content features and applying machine learning algorithms. Sustainability, 15( 8), p. 6662.
[14]	Färber, M. , Qurdina, A . and Ahmedi, L. , 2019, September. Identifying Twitter Bots Using a Convolutional Neural Network. In CLEF (Working Notes).
[15]	Garcia-Silva, A. , Berrio, C . and Gomez-Perez, J.M. , 2021. Understanding transformers for bot detection in Twitter. arXiv preprint arXiv:2104.06182.
[16]	Echeverrï£¡ a, J. , De Cristofaro, E. , Kourtellis, N. , Leontiadis, I. , Stringhini, G . and Zhou, S. , 2018, December. LOBO: Evaluation of generalization deficiencies in Twitter bot classifiers. In Proceedings of the 34th annual computer security applications conference (pp. 137- 146).
[17]	Alhassun, A.S. and Rassam, M.A. , 2022. A combined text-based and metadata-based deep-learning framework for the detection of spam accounts on the social media platform twitter. Processes, 10( 3), p. 439.
[18]	Martín-Gutiérrez, D. , Hernández-Peñaloza, G. , Hernández, A.B. , Lozano-Diez, A . and Álvarez, F. , 2021. A deep learning approach for robust detection of bots in twitter using transformers. IEEE Access, 9, pp. 54591- 54601.
[19]	X Developer Platform, X API, , accessed on October 1, 2024.
[20]	Feng, S. , Wan, H. , Wang, N. , Li, J . and Luo, M., 2021, October. Twibot-20: A comprehensive twitter bot detection benchmark. In Proceedings of the 30th ACM international conference on information & knowledge management (pp. 4485- 4494).
[21]	Hayawi, K. , Mathew, S. , Venugopal, N. , Masud, M.M. and Ho, P.H., 2022. DeeProBot: a hybrid deep neural network model for social bot detection based on user profile data. Social Network Analysis and Mining, 12( 1), p. 43.
[22]	Rodríguez-Ruiz, J. , Mata-Sánchez, J.I. , Monroy, R. , Loyola-González, O . and López-Cuevas, A. , 2020. A one-class classification approach for bot detection on Twitter. Computers & Security, 91, p. 101715.