• Feny Nitin Baria
• Shravani Sanjay Agam
• Prathamesh Dasharath Kumbhar
• Rahul Ankush Kure
• DR. Y. D Sinkar

Cyberbullying has emerged as a critical issue on social media platforms, leading to severe psychological and social consequences for individuals. Detecting such abusive behaviour is challenging, especially when users express emotions and opinions using multilingual text mixed with emojis. Traditional text-based detection systems often fail to capture cross-lingual semantics and the emotional cues conveyed through emojis, resulting in decreased detection accuracy. To address this limitation, this paper proposes a Cyberbullying Detection System for Multilingual Text with Emoji Support, integrating advanced Natural Language Processing (NLP) and deep learning techniques. The model utilizes multilingual embeddings such as mBERT and MuRIL to understand semantic relationships across languages like English, Hindi, and other regional dialects. Furthermore, emojis are analysed as semantic amplifiers, influencing textual sentiment polarity through an emoji–sentiment lexicon and contextual embedding. A hybrid dataset combining multilingual posts with emojis was created and annotated for experimentation. The system was trained using a transformer-based neural architecture and evaluated on multiple performance metrics including accuracy, precision, recall, and F1-score. Experimental results demonstrate a significant improvement over traditional monolingual and emoji-agnostic models, achieving higher robustness and contextual understanding. This research contributes to enhancing digital safety by providing a scalable, emotion-aware, and linguistically diverse framework for automated cyberbullying detection in online communication.

Cyberbullying Detection, Multilingual Text, Emoji Sentiment, Deep Learning, NLP, Social Media, Emotion Analysis

"Cyberbullying Detection In Multilingual Text With Emoji Support", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 11, page no.c556-c562, November-2025, Available :http://www.jetir.org/papers/JETIR2511266.pdf

"Cyberbullying Detection In Multilingual Text With Emoji Support", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 11, page no. ppc556-c562, November-2025, Available at : http://www.jetir.org/papers/JETIR2511266.pdf