AN EXPLAINABLE MACHINE LEARNING FRAMEWORK FOR CYBERBULLYING DETECTION USING NLP AND ENSEMBLE LEARNING

This research presented an Explainable Machine Learning Framework for Cyberbullying Detection using NLP and Ensemble Learning techniques. The framework integrated text preprocessing, TF-IDF feature extraction, feature optimization, ensemble classification, SHAP explainability analysis, and real-time deployment modules. Experimental results demonstrated that the proposed framework effectively identifies cyberbullying content with high classification performance and improved interpretability. SHAP explainability analysis enhanced transparency by identifying influential textual features contributing toward prediction outcomes. The developed framework provides an intelligent, scalable, and transparent solution for automated cyberbullying detection in modern social media platforms.

[1] T. Davidson, D. Warmsley, M. Macy, and I. Weber, “Automated Hate Speech Detection and the Problem of Offensive Language,” in Proc. 11th Int. AAAI Conf. Web and Social Media (ICWSM), Montréal, Canada, 2017, pp. 512–515. [2] P. Badjatiya, S. Gupta, M. Gupta, and V. Varma, “Deep Learning for Hate Speech Detection in Tweets,” in Proc. 26th Int. Conf. World Wide Web Companion, 2017, pp. 759–760. [3] S. Lundberg and S.-I. Lee, “A Unified Approach to Interpreting Model Predictions,” in Advances in Neural Information Processing Systems (NeurIPS), vol. 30, 2017. [4] D. Nandini and U. Schmid, “Explaining Hate Speech Classification with Model-Agnostic Methods,” in Proceedings of the Workshop on Text Mining and Generation (TMG), CEUR Workshop Proceedings, 2022. [5] S. Kumbam, M. Paoletti, and S. Marchand-Maillet, “Explainability and Adversarial Robustness for Hate Speech Detection Models,” in Proceedings of the International AAAI Conference on Web and Social Media (ICWSM), 2023. [6] J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding,” in Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL-HLT), Minneapolis, MN, USA, 2019, pp. 4171–4186. [7] F. Pedregosa et al., “Scikit-learn: Machine Learning in Python,” Journal of Machine Learning Research, vol. 12, pp. 2825–2830, 2011. [8] S. Bird, E. Klein, and E. Loper, Natural Language Processing with Python. Sebastopol, CA, USA: O’Reilly Media, 2009. [9] F. Chollet, Deep Learning with Python. Shelter Island, NY, USA: Manning Publications, 2018. [10] C. C. Aggarwal and C. Zhai, Mining Text Data. Boston, MA, USA: Springer, 2012.