">

Cyber bullying detection and alert system for school


EOI: 10.11242/viva-tech.01.09.42

Download Full Text here



Citation

Pallavi Mohapatra, Vaishali Shimpi, Mahek Shaikh , Rashmi Borse , Saloni Salvi " Cyber bullying detection and alert system for school”. ", VIVA-IJRI Volume 1, Issue 9, Article 42, pp. 1-11, 2026. Published by Computer Engineering Department, VIVA Institute of Technology, Virar, India.

Abstract

Cyberbullying has become a persistent challenge in digitally meditated school environments, where student communication increasingly occurs through online messaging platforms, school-managed communication systems. Unlike traditional bullying, harmful interactions can occur continuously, making manual monitoring and delayed reporting ineffective. This paper presents CyberShield, an AI-driven cyberbullying detection and alert framework specifically designed for school communication ecosystems. The system combines natural language processing with supervised machine-learning techniques to analyze student text messages and flag potentially harmful content in real time. The architecture includes preprocessing, statistical feature extraction, classification, and an alert module that enables human review and administrative intervention. The framework was evaluated on a processed HateXplain dataset containing 19,200 samples. TF-IDF features were used with several classical machine-learning models, and a hybrid pipeline combining random forest classification with rule-based severity assessment achieved 94% accuracy, outperforming baseline approaches. The system is structured for deployment within controlled school platforms, supporting explainable alerts, structured reporting, and timely intervention while maintaining human oversight for ethical compliance.

Keywords

AI-based monitoring, Artificial Intelligence, Cyberbullying, Machine Learning, Natural Language Processing, Text classification..

References

  1. P. Fortuna and S. Nunes, “A survey on automatic detection of hate speech in text,” ACM Computing Surveys, vol. 51, no. 4, pp. 1–30, 2018.
  2. M. Schmidt and M. Wiegand, “A survey on hate speech detection using natural language processing,” in Proc. SocialNLP, Paris, France, 2017, pp. 1–10.
  3. B. Vidgen, S. Hale, E. Guest, H. Margetts, and L. Derczynski, “Detecting abusive language using supervised machine learning,” Journal of Artificial Intelligence Research, vol. 74, pp. 1–34, 2022.
  4. H. Rosa, P. Pereira, R. Ribeiro, et al., “Context-aware cyberbullying detection using hybrid NLPtechniques,” Expert Systems with Applications, vol. 209, 2023.
  5. M. Dadvar, D. Trieschnigg, R. Ordelman, and F. de Jong, “Improving cyberbullying detection with user context,” in Proc. 35th European Conference on Information Retrieval (ECIR), Moscow, Russia, 2013, pp. 693–696.
  6. P. Agrawal and A. Awekar, “Deep learning for detecting cyberbullying across multiple social media platforms,” in Proc. 39th European Conference on Information Retrieval (ECIR), Aberdeen, UK, 2018, pp. 141–153.
  7. B. Vidgen and L. Derczynski, “Directions in abusive language training data: A systematic review,” in Proc. ACL, 2021.
  8. B. Mathew, P. Saha, H. Tharad, et al., “Thou shalt not hate: Countering online hate speech,” in Proc. International AAAI Conference on Web and Social Media (ICWSM), 2021.
  9. K. Dinakar, B. Jones, C. Havasi, H. Lieberman, and R. Picard, “Modeling textual cyberbullying,” in Proc. ICWSM, 2011.
  10. T. Davidson, D. Warmsley, M. Macy, and I. Weber, “Automated hate speech detection and the problem of offensive language,” in Proc. ICWSM, Montreal, Canada, 2017, pp. 512–515.
  11. M. Zampieri, S. Malmasi, P. Nakov, S. Rosenthal, N. Farra, and R. Kumar, “Predicting the type and target of offensive posts in social media,” in Proc. NAACL-HLT, 2019.
  12. T. Mandl, S. Modha, P. Majumder, et al., “Overview of the HASOC track at FIRE 2019: Hate speech and offensive content identification,” in Proc. FIRE, 2019.
  13. B. Vidgen, A. Yasseri, and H. Margetts, “HateXplain: A benchmark dataset for explainable hate speech detection,” in Proc. AAAI Conference on Artificial Intelligence, 2021.
  14. R. M. Kowalski, G. W. Giumetti, A. N. Schroeder, and M. R. Lattanner, “Bullying in the digital age: A critical review and meta-analysis of cyberbullying research,” Psychological Bulletin, vol. 140, no. 4, pp. 1073–1137, 2014.
  15. J. W. Patchin and S. Hinduja, “Cyberbullying and self-harm,” Journal of School Health, vol. 80, no. 12, pp. 614–621, 2010.
  16. A. Bohra, D. Vijay, V. Singh, S. Akhtar, and M. Shrivastava, “A dataset of Hindi-English code-mixed social media text for hate speech detection,” in Proc. EMNLP Workshop, 2018.
  17. B. Vidgen and L. Derczynski, “Challenges and opportunities in abusive language detection,”Computational Linguistics, 2021.
  18. A. Ganesh et al., “Multilingual cyberbullying detection using hybrid deep learning approaches,”IEEE Access, 2024.
  19. S. García-Méndez and J. Arriba-Pérez, “Explainable cyberbullying detection using large language models,” Expert Systems with Applications, 2024.
  20. T. Brown et al., “Language models are few-shot learners,” in Proc. NeurIPS, 2020.
  21. J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of deep bidirectional transformers for language understanding,” in Proc. NAACL-HLT, 2019..
  22. P. Lewis et al., “Retrieval-augmented generation for knowledge-intensive NLP tasks,” in Proc.NeurIPS, 2020.
  23. Z. Waseem and D. Hovy, “Predictive features for hate speech detection on Twitter,” in Proc.NAACL Student Research Workshop, 2016, pp. 88–93.
  24. S. Badjatiya, M. Gupta, M. Gupta, and V. Varma, “Deep learning for hate speech detection in tweets,” in Proc. WWW Companion, 2017, pp. 759–760.
  25. R. Saha, S. Sharma, and A. Saxena, “Cyberbullying detection: Challenges and future directions,”IEEE Access, vol. 9, pp. 10123–10135, 2021.