Investigation of deep neural network architecture for cyberbullying detection over social media
Introduction: Nowadays, there has been a significant increase in cases of cyberbullying on digital devices and platforms such as Facebook, Instagram, Snapchat, and TikTok.
Problem: Many state-of-the-art approaches have been introduced for the detection of cyberbullying activities. However, the affordability of high-quality data resources, along with restrictions on their access, limits the applicability of these state-of-the-art approaches.
Objective: The detection of cyberbullying activities is of societal importance and has gained increasing prominence in research.
Methodology: In this paper, we explored convolutional neural networks for cyberbullying detection (CNN-CBD) architecture for the classification task and reported their performance on real-world databases such as Twitter, Wikipedia, and Formspring. We also compared the CNN-CBD performance with baseline machine learning (ML) models. Various issues regarding the handling of real-world databases and the selection of the most suitable deep neural network (DNN) model are reported and discussed in detail.
Results: Experiments showed that the proposed CNN-CBD model outperformed traditional ML algorithms in cyberbullying detection, achieving an accuracy of 97%.
Conclusions: We concluded that the proposed CNN-CBD model outperformed the existing baseline models.
How to Cite
License
Copyright (c) 2026 Ingeniería Solidaria
This work is licensed under a Creative Commons Attribution 4.0 International License.
Cession of rights and ethical commitment
As the author of the article, I declare that is an original unpublished work exclusively created by me, that it has not been submitted for simultaneous evaluation by another publication and that there is no impediment of any kind for concession of the rights provided for in this contract.
In this sense, I am committed to await the result of the evaluation by the journal Ingeniería Solidaría before considering its submission to another medium; in case the response by that publication is positive, additionally, I am committed to respond for any action involving claims, plagiarism or any other kind of claim that could be made by third parties.
At the same time, as the author or co-author, I declare that I am completely in agreement with the conditions presented in this work and that I cede all patrimonial rights, in other words, regarding reproduction, public communication, distribution, dissemination, transformation, making it available and all forms of exploitation of the work using any medium or procedure, during the term of the legal protection of the work and in every country in the world, to the Universidad Cooperativa de Colombia Press.
[1] R. Shetgiri, “Bullying and victimization among children,” Advances in Pediatrics, vol. 60, no. 1, pp. 33–51, jul. 2013. DOI: https://doi.org/10.1016/j.yapd.2013.04.004
[2] D. Halpern, M. Piña y J. Vásquez, “Loneliness, personal and social well-being: Towards a conceptualization of the effects of cyberbullying / Soledad, bienestar social e individual: hacia una conceptualización de los efectos del cyberbullying,” Cultura y Educación, vol. 29, no. 4, pp. 703–727, 2017. DOI: https://doi.org/10.1080/11356405.2017.1370818
[3] S. Balakrishna, Y. Gopi y V. K. Solanki, “Comparative analysis on deep neural network models for detection of cyberbullying on social media,” Ingeniería Solidaria, vol. 18, no. 1, pp. 1–33, 2022. DOI: https://doi.org/10.16925/2357-6014.2022.01.05
[4] U. Bretschneider, T. Wöhner y R. Peters, “Detecting online harassment in social networks,” en Proc. 35th Int. Conf. on Information Systems, 2014, pp. 1–14.
[5] J. Bayzick, A. Kontostathis y L. Edwards, “Detecting the presence of cyberbullying using computer software,” 2011, pp. 1–2.
[6] K. Reynolds, A. Kontostathis y L. Edwards, “Using machine learning to detect cyberbullying,” en Proc. 10th Int. Conf. on Machine Learning and Applications (ICMLA), vol. 2, dic. 2011, pp. 241–244, doi:10.1109/ICMLA.2011.152. DOI: https://doi.org/10.1109/ICMLA.2011.152
[7] J. Xu, K. Jun, X. Zhu y A. Bellmore, “Learning from bullying traces in social media,” en Proc. Assoc. for Computational Linguistics: Human Language Technologies, 2012, pp. 656–666.
[8] A. Kontostathis, L. Edwards y A. Leatherman, “Text mining and cybercrime,” en Text Mining: Applications and Theory. Hoboken, NJ, EE. UU.: Wiley, 2010, pp. 1–14. DOI: https://doi.org/10.1002/9780470689646.ch8
[9] J. Xu, K. Jun, X. Zhu y A. Bellmore, “Learning from bullying traces in social media,” en Proc. Conf. of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2012, pp. 656–666.
[10] C. Van Hee et al., “Detection and fine-grained classification of cyber-bullying events,” en Proc. Int. Conf. on Recent Advances in Natural Language Processing (RANLP), 2015, pp. 672–680.
[11] R. Salsabila, R. Sarno, I. Ghozali y K. R. Sungkono, “Improving cyberbullying detection through multi-level machine learning,” International Journal of Emerging Trends in Engineering Research, vol. 14, no. 2, 2024. DOI: https://doi.org/10.11591/ijece.v14i2.pp1779-1787
[12] P. Yi y A. Zubiaga, “D-XCB: Data-independent debiasing for fair and accurate transformer-based cyberbullying detection,” arXiv preprint arXiv:2402.16458, feb. 2024. DOI: https://doi.org/10.1609/icwsm.v19i1.35924
[13] K. Maity, R. Jain, P. Jha y S. Saha, “Explainable cyberbullying detection in Hinglish: A generative approach,” IEEE Transactions on Computational Social Systems, 2023. DOI: https://doi.org/10.1109/TCSS.2023.3333675
[14] A. Almomani et al., “Image cyberbullying detection and recognition using transfer deep machine learning,” International Journal of Cognitive Computing in Engineering, vol. 5, pp. 14–26, 2023. DOI: https://doi.org/10.1016/j.ijcce.2023.11.002
[15] H. Saini, H. Mehra y R. Rani, “Enhancing cyberbullying detection: A comparative study of ensemble CNN–SVM and BERT models,” Social Network Analysis and Mining, vol. 14, no. 1, 2023. DOI: https://doi.org/10.1007/s13278-023-01158-w
[16] R. Kumar y B. Bhat, “A study of machine learning-based models for detection, control, and mitigation of cyberbullying in online social media,” International Journal of Information Security, vol. 21, pp. 1409–1431, 2022. DOI: https://doi.org/10.1007/s10207-022-00600-y
[17] M. Dadvar, D. Trieschnigg, R. Ordelman y F. de Jong, “Improving cyberbullying detection with user context,” 2015, pp. 2–5.
[18] H. Hosseinmardi et al., “Detection of cyberbullying incidents on the Instagram social network,” 2014. DOI: https://doi.org/10.1007/978-3-319-27433-1_4
[19] V. Nahar, S. Al-Maskari, X. Li y C. Pang, “Semi-supervised learning for cyberbullying detection in social networks,” en Proc. Australasian Database Conf., 2014, pp. 160–171. DOI: https://doi.org/10.1007/978-3-319-08608-8_14
[20] J. M. Hilbe, Logistic Regression Models. Boca Raton, FL, EE. UU.: CRC Press, 2009. DOI: https://doi.org/10.1201/9781420075779
[21] Y. W. Chang y C. J. Lin, “Feature ranking using linear SVM,” en Causation and Prediction Challenge, dic. 2008, pp. 53–64.
[22] J. R. Quinlan, “Simplifying decision trees,” International Journal of Man–Machine Studies, vol. 27, no. 3, pp. 221–234, sep. 1987. DOI: https://doi.org/10.1016/S0020-7373(87)80053-6
[23] B. Xu, X. Guo, Y. Ye y J. Cheng, “An improved random forest classifier for text categorization,” Journal of Computers, vol. 7, no. 12, pp. 2913–2920, 2012. DOI: https://doi.org/10.4304/jcp.7.12.2913-2920
[24] S. Tan, “An effective refinement strategy for KNN text classifier,” Expert Systems with Applications, vol. 30, no. 2, pp. 290–298, 2006. DOI: https://doi.org/10.1016/j.eswa.2005.07.019
[25] A. M. Kibriya, E. Frank, B. Pfahringer y G. Holmes, “Multinomial naive Bayes for text categorization revisited,” en Proc. Australasian Joint Conf. on Artificial Intelligence. Berlín, Alemania: Springer, dic. 2004, pp. 488–499. DOI: https://doi.org/10.1007/978-3-540-30549-1_43
[26] M. Zareapoor y P. Shamsolmoali, “Application of credit card fraud detection based on bagging ensemble classifier,” Procedia Computer Science, vol. 48, pp. 679–685, 2015. DOI: https://doi.org/10.1016/j.procs.2015.04.201
[27] M. A. Al-Ajlan y M. Ykhlef, “A deep learning algorithm for cyberbullying detection,” International Journal of Advanced Computer Science and Applications, no. 9, 2018. DOI: https://doi.org/10.14569/IJACSA.2018.090927
[28] F. Chollet, “Keras,” GitHub, 2015. [En línea]. Disponible en: https://github.com/fchollet/keras
[29] F. Pedregosa et al., “Scikit-learn: Machine learning in Python,” Journal of Machine Learning Research, vol. 12, pp. 2825–2830, nov. 2011.
[30] M. Abadi et al., “TensorFlow: A system for large-scale machine learning,” en Proc. 12th USENIX Symp. on Operating Systems Design and Implementation (OSDI’16), 2016, pp. 265–283.
[31] Y. Bengio, R. Ducharme, P. Vincent y C. Jauvin, “A neural probabilistic language model,” Journal of Machine Learning Research, vol. 3, pp. 1137–1155, feb. 2003.
[32] C. Emmery et al., “Current limitations in cyberbullying detection: On evaluation criteria, reproducibility, and data scarcity,” arXiv preprint arXiv:1910.11922, 2019.
