GLOVE-EMBEDDED ATTENTION BILSTM NETWORKS FOR ENHANCED MULTICLASSIFICATION OF TWEETS IN CYBERBULLYING DETECTION ON ONLINE CONTENT
DOI:
https://doi.org/10.37943/22PSRO3633Keywords:
cyberbullying detection, deep learning, natural language processing, GloVe embeddings, BiLSTM networks, self-attention mechanisms, social mediaAbstract
This paper offers a neural network method for social media cyberbullying detection and classification. The model uses GloVe-embedded BiLSTM networks with self-attention to recognize language and semantic patterns. The research uses advanced machine learning methods to fight cyberbullying and suggests ways to improve cyberbullying detection systems' precision and ethics. The proposed paradigm addresses several cyberbullying levels and forms, enabling targeted interventions and victim support. GloVe implementations do semantic processing, BiLSTM networks sequentially learn, and self-attention mechanisms focus contextual analysis in the model. Word clouds show the abundance and relevance of phrases across several cyberbullying categories, revealing common themes and vocabulary. Tweet lengths, confusion matrix, training and validation loss and accuracy metrics, and ROC curves included in the dataset. The logistic regression model's ROC curve investigation shows substantial classification performance across multiple categories with AUC values between 0.905 and 0.997. The best model for age categorization has an AUC of 0.997, followed by religion (0.996) and ethnicity (0.993). Gender classification has an AUC of 0.979, whereas cyberbullying and non-cyberbullying have 0.921 and 0.905, respectively. The logistic regression model's ROC curve investigation shows substantial classification performance across multiple categories with AUC values between 0.905 and 0.997. The best model for age categorization has an AUC of 0.997, followed by religion (0.996) and ethnicity (0.993). Gender classification has an AUC of 0.979, whereas cyberbullying and non-cyberbullying have 0.921 and 0.905, respectively. The study encourages AI technology for social good and emphasizes the need to improve categorization algorithms to handle cyberbullying language's complex changes. Expanding training datasets, exploring hybrid modeling methodologies, and creating AI application ethics must be future goals.
References
Atif, A., Zafar, A., Wasim, M., Waheed, T., Ali, A., Ali, H., & Shah, Z. (2024). Cyberbullying Detection and Abuser Profile Identification on Social Media for Roman Urdu. IEEE Access. https://doi.org/10.1109/ACCESS.2024.3445288
Talpur, K. R., Yuhaniz, S. S., & Amir, N. N. B. (2020). Cyberbullying detection: Current trends and future directions. Journal of Theoretical and Applied Information Technology, 98(16), 3197-3208. https://core.ac.uk/download/pdf/425547762.pdf
Ahmadinejad, M., Shahriar, N., & Fan, L. (2023). Self-Training for Cyberbully Detection: Achieving High Accuracy with a Balanced Multi-Class Dataset (Doctoral dissertation, PhD thesis, Faculty of Graduate Studies and Research, University of Regina). https://www.proquest.com/openview/2e6b484d78e3a1fe0486ec1217dd574c/1?pq-origsite=gscholar&cbl=18750&diss=y
Rao, M. P., Kota, N., Nidumukkala, D., Madoori, M., & Ali, D. (2024, April). Enhancing Online Safety: Cyberbullying Detection with Random Forest Classification. In 2024 10th International Conference on Communication and Signal Processing (ICCSP) (pp. 389-393). IEEE. https://doi.org/10.1109/ICCSP60870.2024.10543598
Kaarthika, R., & Hemamalini, R. (2024, July). Enhancing Cyberbullying Detection Through Keyword Filtering: A Comparative Study of ML and DL Approaches. In 2024 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT) (pp. 1-6). IEEE. https://doi.org/10.1109/IConSCEPT61884.2024.10627823
Saeid, A., Kanojia, D., & Neri, F. (2024, June). Decoding Cyberbullying on Social Media: A Machine Learning Exploration. In 2024 IEEE Conference on Artificial Intelligence (CAI) (pp. 425-428). IEEE. https://doi.org/10.1109/CAI59869.2024.00084
Dharani, M., & Sathya, S. (2024). Deep Learning Algorithms with Adam Optimization for Detecting of Cyberbullying Comments. Nanotechnology Perceptions, 627-639. https://nano-ntp.com/index.php/nano/article/download/746/676/1257
Sultan, D., Omarov, B., Kozhamkulova, Z., Kazbekova, G., Alimzhanova, L., Dautbayeva, A., ... & Abdrakhmanov, R. (2023). A Review of Machine Learning Techniques in Cyberbullying Detection. Computers, Materials & Continua, 74(3). https://doi.org/10.32604/cmc.2023.033682
Kumar, C., Kumar, K. A., Gupta, S., & Sardar, T. H. (2024, March). Cyberbullying detection based on the fusion of DistilBERT and SIMHASH Technique. In 2024 2nd International Conference on Artificial Intelligence and Machine Learning Applications Theme: Healthcare and Internet of Things (AIMLA) (pp. 1-4). IEEE. https://doi.org/10.1109/AIMLA59606.2024.10531427
Hoque, M. N., Chakraborty, P., & Seddiqui, M. H. The Challenges and Approaches during the Detection of Cyberbullying Text for Low-resource Language: A Literature. https://doi.org/10.37936/ecti-cit.2023172.248039
Saranyanath, K. P., Shi, W., & Corriveau, J. P. (2022, September). Cyberbullying Detection using Ensemble Method. In CS & IT Conference Proceedings (Vol. 12, No. 15). CS & IT Conference Proceedings. https://doi.org/10.22215/etd/2022-15070
Sari, T. I., Ardilla, Z. N., Hayatin, N., & Maskat, R. (2022). Abusive comment identification on Indonesian social media data using hybrid deep learning. IAES International Journal of Artificial Intelligence, 11(3), 895-904. https://doi.org/10.11591/ijai.v11.i3.pp895-904
Liu, M. (2023, July). A Creativity Survey of Cyberbullying Classification Based on Social Network Analysis. In Proceedings of the 2nd International Conference on Mathematical Statistics and Economic Analysis, MSEA 2023, May 26–28, 2023, Nanjing, China. https://doi.org/10.4108/eai.26-5-2023.2334259
Bhamidi, M., Nandyala, M., Dayalan, R., Karthik, N., & Vani, V. (2024, February). COOL: Classification of Online Offensive Language Using Machine Learning and Deep Learning. In International Conference on Computational Intelligence in Data Science (pp. 87-97). Cham: Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-69982-5_7
Mohite, S. S., Attar, V., & Kalamkar, S. (2022, October). Shaming tweets detection on Twitter using Machine learning Algorithms. In 2022 IEEE 3rd Global Conference for Advancement in Technology (GCAT) (pp. 1-6). IEEE. https://doi.org/10.1109/GCAT55367.2022.9972100
Ismail, A. A., & Yusoff, M. (2022). An efficient hybrid LSTM-CNN and CNN-LSTM with GloVe for text multi-class sentiment classification in gender violence. International Journal of Advanced Computer Science and Applications, 13(9). https://doi.org/10.14569/IJACSA.2022.0130999
Ibrahim, Y. M., Essameldin, R., & Darwish, S. M. (2024). An Adaptive Hate Speech Detection Approach Using Neutrosophic Neural Networks for Social Media Forensics. Computers, Materials & Continua, 79(1). https://doi.org/10.32604/cmc.2024.047840
Koshiry, A. M. E., Eliwa, E. H. I., Abd El-Hafeez, T., & Omar, A. (2023). Arabic toxic tweet classification: leveraging the arabert model. Big Data and Cognitive Computing, 7(4), 170. https://doi.org/10.3390/bdcc7040170
Sharma, D. K., Singh, B., Agarwal, S., Pachauri, N., Alhussan, A. A., & Abdallah, H. A. (2023). Sarcasm detection over social media platforms using hybrid ensemble model with fuzzy logic. Electronics, 12(4), 937. https://doi.org/10.3390/electronics12040937
Slobodzian, V., Molchanova, M., Kovalchuk, O., Sobko, O., Mazurets, O., Barmak, O., & Krak, I. (2022, September). An Approach Based on the Visualization Model for the Ukrainian Web Content Classification. In 2022 12th International Conference on Advanced Computer Information Technologies (ACIT) (pp. 400-405). IEEE. https://doi.org/10.1109/ACIT54803.2022.9913162
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Articles are open access under the Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Authors who publish a manuscript in this journal agree to the following terms:
- The authors reserve the right to authorship of their work and transfer to the journal the right of first publication under the terms of the Creative Commons Attribution License, which allows others to freely distribute the published work with a mandatory link to the the original work and the first publication of the work in this journal.
- Authors have the right to conclude independent additional agreements that relate to the non-exclusive distribution of the work in the form in which it was published by this journal (for example, to post the work in the electronic repository of the institution or publish as part of a monograph), providing the link to the first publication of the work in this journal.
- Other terms stated in the Copyright Agreement.