MUMBAI, India, March 13 -- Intellectual Property India has published a patent application (202641024617 A) filed by Nri Institute Of Technology; Ms. K. Bhanu Sree; Ms. D. V. N. Manasiza; Mr. B. Akhil; Ms. M. Deemanth Kumari; Mr. B. Phanindra Kumar; and Mr. P. Venu Gopal, Eluru, Andhra Pradesh, on March 2, for 'cyberbullying detection on social media using deep learning.'
Inventor(s) include Ms. K. Bhanu Sree; Ms. D. V. N. Manasiza; Mr. B. Akhil; Ms. M. Deemanth Kumari; Mr. B. Phanindra Kumar; and Mr. P. Venu Gopal.
The application for the patent was published on March 13, under issue no. 11/2026.
According to the abstract released by the Intellectual Property India: "The present study proposes an advanced cyberbullying detection framework for social media platforms using deep learning and transformer-based architectures. The system is designed to automatically identify harmful, abusive, or bullying content from unstructured textual data posted by users online. The proposed framework integrates data preprocessing, noise removal, tokenization, and semantic embedding into a unified processing pipeline that converts raw text into structured numerical representations suitable for model training. Multiple neural network architectures, including Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM) networks, Convolutional Neural Networks (CNN), and attention-based transformer models, are implemented and evaluated under consistent experimental conditions to ensure fair performance comparison. These models capture contextual dependencies, sequential patterns, and semantic nuances essential for detecting implicit and explicit forms of cyberbullying. Performance is assessed using robust evaluation metrics such as accuracy, precision, recall, F1-score, and ROC-AUC. Experimental results demonstrate that bidirectional transformer models with contextual embeddings achieve superior accuracy and reliability in identifying harmful online content."
Disclaimer: Curated by HT Syndication.
