AI-Powered Frameworks for the Detection and Prevention of Cyberbullying Across Social Media Ecosystems
DOI:
https://doi.org/10.70063/techcompinnovations.v2i1.59Keywords:
Cyberbullying Detection, Text Classification, Machine Learning, Deep Learning, Social MediaAbstract
This study presents an advanced AI-powered framework to detect and prevent cyberbullying across diverse social media platforms using a multiclass classification approach. Addressing the growing complexity and linguistic diversity of online abuse, the research integrates various machine learning (RF, LR, SVM) and deep learning (Bi-LSTM, BERT) models trained on a balanced dataset covering bullying categories based on religion, age, ethnicity, gender, and neutral content. Data preprocessing, tokenization, feature extraction via TF-IDF and CountVectorizer, and class balancing using SMOTE were applied to enhance model accuracy. The proposed system further supports real-time detection through social media APIs, offering dynamic monitoring and intervention capabilities. Among the tested models, Random Forest and BERT achieved the highest classification performance with 94% accuracy. Despite its robust architecture, limitations include dependence on English-language datasets, exclusion of multimodal data (e.g., memes, audio), and API restrictions that challenge scalability. Future development will focus on incorporating vision-language models and optimizing the system for real-time, multilingual, and multimodal environments. This study contributes to digital safety efforts by proposing a scalable and adaptive detection system suitable for safeguarding users from evolving forms of online harassment.
Downloads
References
Al-Dabet, S., ElMassry, A., Alomar, B., & Alshamsi, A. (2023, March). Transformer-based Arabic offensive speech detection. 2021 International Conference on Emerging Smart Computing and Informatics (ESCI), 1–6. https://doi.org/10.1109/esci56872.2023.10100134
Alothali, E., Alashwal, H., Salih, M., & Hayawi, K. (2021, October). Real-time detection of social bots on Twitter using machine learning and Apache Kafka. 2021 5th Cyber Security in Networking Conference (CSNet). https://doi.org/10.1109/csnet52717.2021.9614282
Balet, T., Vo, Q., Salem, O., & Mehaoua, A. (2023, June). Cyberbullying detection on tweets from Twitter using machine learning algorithms. 2023 International Conference on Intelligent Computing, Communication, Networking and Services (ICCNS), 3, 177–182. https://doi.org/10.1109/iccns58795.2023.10193450
Beniwal, R., Jha, S., Mehta, S., & Dhiman, R. (2023, June). Cyberbullying detection using deep learning models in Bengali language. 2023 3rd International Conference on Intelligent Technologies (CONIT), 1–5. https://doi.org/10.1109/conit59222.2023.10205775
Cyberbullying classification. (2022, January 17). Kaggle. https://www.kaggle.com/datasets/andrewmvd/cyberbullying-classification
Dalvi, R. R., Chavan, S. B., & Halbe, A. (2020, May). Detecting a Twitter cyberbullying using machine learning. 2022 6th International Conference on Intelligent Computing and Control Systems (ICICCS). https://doi.org/10.1109/iciccs48265.2020.9120893
Dhanalakshmi, D., Rani, N. D., Pendam, K., Hariharan, S., Kukreja, V., & Jayakshata, P. (2023, June). Machine learning based intelligent cyberbullying avoidance system. 2023 International Conference on Sustainable Computing and Smart Systems (ICSCSS), 9, 1594–1597. https://doi.org/10.1109/icscss57650.2023.10169376
Gupta, S., Vadgama, U., & Vedhavathy, T. R. (2023, April). Identification and labeling of textual cyberbullying using BiLSTM and BERT. 2023 International Conference on Networking and Communications (ICNWC), 1–5. https://doi.org/10.1109/icnwc57852.2023.10127308
Islam, M., Rahman, M., Ahmed, M. T., Islam, A. Z. M., Das, D., & Hoque, M. M. (2023, February). Sexual harassment detection using machine learning and deep learning techniques for Bangla text. 2023 International Conference on Electrical, Computer and Communication Engineering (ECCE). https://doi.org/10.1109/ecce57851.2023.10101522
Jeevitha, R., Chaitanya, K., Mathesh, N., Nithyanarayanan, B., & Darshan, P. (2023, March). Using machine learning to identify instances of cyberbullying on social media. 2022 International Conference on Sustainable Computing and Data Communication Systems (ICSCDS), 8, 207–212. https://doi.org/10.1109/icscds56580.2023.10104720
Matias, S. M. M., Costales, J. A., & De Los Santos, C. M. (2022, August). A framework for cybercrime prediction on Twitter tweets using text-based machine learning algorithm. 2022 5th International Conference on Pattern Recognition and Artificial Intelligence (PRAI), 10, 235–240. https://doi.org/10.1109/prai55851.2022.9904212
Nemade, S., Mane, S. B., & Nandgaonkar, S. (2023, April). Detection and classification of aggressive comments and hate speech. 2022 International Conference on Computational Intelligence and Sustainable Engineering Solutions (CISES), 14, 55–60. https://doi.org/10.1109/cises58720.2023.10183445
Patidar, M. (2021, November). Cyber bullying detection for Twitter using ML classification algorithms. International Journal for Research in Applied Science and Engineering Technology, 9(11), 24–29. https://doi.org/10.22214/ijraset.2021.38701
Pawar, V., Jose, D. V., & Patil, A. (2022, December). Explainable AI method for cyber bullying detection. 2022 IEEE 2nd International Conference on Mobile Networks and Wireless Communications (ICMNWC). https://doi.org/10.1109/icmnwc56175.2022.10031652
Perez, C., & Karmakar, S. (2023, March). An NLP-assisted Bayesian time-series analysis for prevalence of Twitter cyberbullying during the COVID-19 pandemic. Social Network Analysis and Mining, 13(1). https://doi.org/10.1007/s13278-023-01053-4
Pericherla, S., & Ilavarasan, E. (2020). A study of machine learning approaches to detect cyberbullying. In Lecture Notes in Networks and Systems (pp. 369–377). https://doi.org/10.1007/978-981-15-5397-4_38
Pradhan, A., Yatam, V. M., & Bera, P. (2020, June). Self-attention for cyberbullying detection. 2020 International Conference on Cyber Situational Awareness, Data Analytics and Assessment (CyberSA). https://doi.org/10.1109/cybersa49311.2020.9139711
Rachidi, R., Ouassil, M. A., Errami, M., Cherradi, B., Hamida, S., & Silkan, H. (2023, May). Social media’s toxic comments detection using artificial intelligence techniques. 2023 3rd International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET). https://doi.org/10.1109/iraset57153.2023.10153015
Raj, M., Singh, S., Solanki, K., & Selvanambi, R. (2022, July). An application to detect cyberbullying using machine learning and deep learning techniques. SN Computer Science, 3(5). https://doi.org/10.1007/s42979-022-01308-5
Romsaiyud, W., Nakornphanom, K. N., Prasertsilp, P., Nurarak, P., & Konglerd, P. (2017, February). Automated cyberbullying detection using clustering appearance patterns. 2017 9th International Conference on Knowledge and Smart Technology (KST), 242–247. https://doi.org/10.1109/kst.2017.7886127
Sainju, K. D., Mishra, N., Kuffour, A., & Young, L. (2021, February). Bullying discourse on Twitter: An examination of bully-related tweets using supervised machine learning. Computers in Human Behavior, 120, 106735. https://doi.org/10.1016/j.chb.2021.106735
Selvaraj, P. A., Jagadeesan, M., Saravanan, T. M., Shaheela, Y., Pandey, S. K., & Sowmithra, M. (2023, January). Detection of personal attacks in mobbing on social media using deep learning techniques. 2022 International Conference on Computer Communication and Informatics (ICCCI). https://doi.org/10.1109/iccci56745.2023.10128345
Shanto, S. B., Islam, M. J., & Samad, M. A. (2023, February). Cyberbullying detection using deep learning techniques on Bangla Facebook comments. 2023 International Conference on Intelligent Systems, Advanced Computing and Communication (ISACC), 1–7. https://doi.org/10.1109/isacc56298.2023.10083690
Tahmasbi, N., & Rastegari, E. (2018, December). A socio-contextual approach in automated detection of public cyberbullying on Twitter. ACM Transactions on Social Computing, 1(4), 1–22. https://doi.org/10.1145/3290838
Thangarasu, G., & Alla, K. R. (2023, May). Detection of cyberbullying tweets in Twitter media using random forest classification. 2023 IEEE 13th Symposium on Computer Applications & Industrial Electronics (ISCAIE). https://doi.org/10.1109/iscaie57739.2023.10165118
Van Hee, C., et al. (2018, October). Automatic detection of cyberbullying in social media text. PLOS ONE, 13(10), e0203794. https://doi.org/10.1371/journal.pone.0203794
Venu, V. S., Shanmugasundaram, H., Seelam, M. R., Kotha, V. V. R., Muthyala, S. S. R., & Kansal, S. (2023, May). Detection of cyberbullying on user tweets and Wikipedia text using machine learning. 2023 2nd International Conference on Applied Artificial Intelligence and Computing (ICAAIC), 12, 327–332. https://doi.org/10.1109/icaaic56838.2023.10140252
Wang, J., Fu, K., & Lu, C.-T. (2020, December). SOSNET: A graph convolutional network approach to fine-grained cyberbullying detection. 2021 IEEE International Conference on Big Data (Big Data). https://doi.org/10.1109/bigdata50022.2020.9378065
Zhang, J., Otomo, T., Li, L., & Nakajima, S. (2019, October). Cyberbullying detection on Twitter using multiple textual features. 2019 IEEE 10th International Conference on Awareness Science and Technology (iCAST), 1–6. https://doi.org/10.1109/icawst.2019.8923186
