• Nitya Shree R
• Divyashree S
• Neha G
• Pooja Kulkarni
• Poornima K

Growing up in a world of instantaneous communication, contemporary "digital natives" have developed limitless relationships. Cyberbullying, or "willful and repeated injuries caused by the use of electronic devices," has become more prevalent because of this quick evolution, which frequently makes it difficult to distinguish between harmful and acceptable behaviors. This study suggests a method for automatically identifying bullying traces on social networks by utilizing natural language processing and machine learning. Using semantic and syntactic sentence attributes, our method effectively clusters documents with bullying content using Growing Hierarchical SOMs. The model was tested on YouTube and Form spring, but it was refined for Twitter. The outcomes show that this unsupervised approach performs well in detecting cyberbullying in a range of contexts.

Cyberbullying Detection, Artificial Intelligence (AI), Machine Learning (ML), Natural Language Processing (NLP), Deep Learning (LSTM, RNN, CNN), Text Mining, Classification, Data Preprocessing, Tokenization, Stop-word Removal, Normalization, Feature Extraction, Bag of Words, TF-IDF, Word2Vec, Social Media Analysis, Real-Time Scalability, Contextual Detection

"Design and Implementation of an AI-Based Cyberbullying Detection System", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 2, page no.a753-a757, February-2025, Available :http://www.jetir.org/papers/JETIR2502097.pdf

"Design and Implementation of an AI-Based Cyberbullying Detection System", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 2, page no. ppa753-a757, February-2025, Available at : http://www.jetir.org/papers/JETIR2502097.pdf