Text Categorization Model for Detecting Cyberbullying Content on Twitter Using Support Vector Machine (SVM) And Naïve Bayes Algorithm

Jonathan Nyekachi  Amadi; Osaki Miller Thom- Manuel

Authors

Jonathan Nyekachi Amadi Department of Computer Science, Ignatius Ajuru University of Education, Port Harcourt, Rivers State, Nigeria
Osaki Miller Thom- Manuel Department of Computer Science, Ignatius Ajuru University of Education, Port Harcourt, Rivers State, Nigeria

Keywords:

Text Categorization Model, Cyberbullying Content, Twitter, Support Vector Machine (SVM), Naïve Bayes Algorithm

Abstract

As social networks such as Twitter expand, so have the means – and frequency of cyberbullying – to a point where it may present material psychological and emotional risks to users. In this study, we design and implement a text categorization model to spot content of cyberbullying on Twitter using Support Vector Machine (SVM) and Naïve Bayes algorithms. Structured text preprocessing techniques such as tokenization, stopword removal, and TF-IDF feature extraction are proposed in the proposed system to convert tweets into feature vectors for the machine learning classification. The pipeline is executed by a computer program developed in Python that combines SVM and Naïve Bayes together to increase the performance of detection and a web-based dashboard enables users to visualize the tested and classified content in close to real-time. The results show that the hybrid model achieves 94.1% accuracy and 93.1% F1-score, which can outpace all single classifiers, and it also can detect subtle cases of the cyberbullying setting, for example, sarcasm and context-dependent harassment compared to the state-of-the-art systems. The results indicate that the proposed model offers a practical, reliable, and scalable solution for monitoring Twitter, providing an effective tool for mitigating harmful online behavior and enhancing safer social media interactions.

References

B. I. Kusuma and A. Nugroho, “Cyberbullying detection on Twitter using the support vector machine method,” J. Tek. Inform., vol. 5, no. 1, 2024.

S. Afrifa and V. Varadarajan, “Cyberbullying detection on Twitter using natural language processing and machine learning techniques,” Int. J. Innov. Technol. Interdiscip. Sci., vol. 5, no. 4, pp. 1069–1080, 2022.

S. Kagi, “Machine learning approaches for cyberbullying detection on Twitter,” J. Sci. Res. Technol., vol. 3, no. 2, pp. 45–53, 2025.

O. M. Fola, A. T. Balarabe, and H. I. Binji, “Cyberbullying detection on Twitter using support vector machine and naïve Bayes algorithms,” Covenant J. Sci. Technol., vol. 7, no. 3, 2025.

A. Muneer and S. Fati, “A comparative analysis of machine learning techniques for cyberbullying detection on Twitter,” Future Internet, vol. 12, no. 11, p. 187, 2020.

R. Patidar, A. Sharma, and R. Verma, “Cyberbullying detection on Twitter using machine learning algorithms,” Int. J. Res. Appl. Sci. Eng. Technol., vol. 9, no. 6, pp. 2413–2419, 2021.

P. Widiyantoro and R. D. Febriyanti, “Comparison of machine learning algorithms for cyberbullying detection in social media text classification,” Telematika: J. Inform. Teknol. Inf., vol. 21, no. 3, pp. 210–218, 2024.

D. S. Ruziqiana, L. Hidayah, and M. A. Rasyidi, “Cyberbullying detection using support vector machine, naïve Bayes, and random forest algorithms,” J. Inform. Tek. Elektro Terap., vol. 12, no. 3, pp. 441–449, 2023.

D. Chatzakou, N. Kourtellis, J. Blackburn, E. De Cristofaro, G. Stringhini, and A. Vakali, “Mean birds: Detecting aggression and bullying on Twitter,” in Proc. ACM Web Sci. Conf., 2019, pp. 13–22.

S. Agrawal and A. Awekar, “Deep learning for detecting cyberbullying across multiple social media platforms,” in Eur. Conf. Inf. Retrieval, 2018, pp. 141–153.

M. Agbaje and O. Afolabi, “Neural network-based cyberbullying and cyber-aggression detection using Twitter text,” Revue d’Intelligence Artificielle, vol. 38, no. 3, pp. 1–12, 2024.

M. S. Akter, H. Shahriar, and A. Cuzzocrea, “A trustable LSTM-autoencoder network for cyberbullying detection on social media using synthetic data,” arXiv preprint arXiv:2308.09722, 2023.

A. F. Alqahtani and M. Ilyas, “A machine learning ensemble model for the detection of cyberbullying in social media,” arXiv preprint arXiv:2402.12538, 2024.

B. I. Kusuma and A. Nugroho, “Cyberbullying detection on Twitter using the support vector machine method,” J. Tek. Inform., vol. 5, no. 1, pp. 33–42, 2024.

M. Fola, A. T. Balarabe, and H. I. Binji, “Cyberbullying detection on Twitter using support vector machine and naïve Bayes algorithms,” Covenant J. Sci. Technol., vol. 7, no. 3, pp. 1–12, 2025.

D. S. Ningsih and R. R. Suryono, “Comparison of naïve Bayes and information gain algorithms in cyberbullying sentiment analysis on Twitter,” J. Tek. Inform., vol. 5, no. 4, 2024.

D. Satyaraj, P. A. Prassath, M. Bhargav, and M. Khajamohiddin, “Implementation of cyberbullying detection in social media using machine learning,” Int. J. Eng. Res. Technol., vol. 12, no. 3, 2023.

P. Widiyantoro and R. D. Febriyanti, “Comparison of algorithms for cyberbullying detection in social media text classification,” Telematika: J. Inform. Teknol. Inf., vol. 21, no. 3, 2025.