MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541122189 A) filed by Vellore Institute Of Technology, Vellore, Tamil Nadu, on Dec. 4, 2025, for 'system and method for detecting cyberbullying-related hate speech using ensemble machine learning.'
Inventor(s) include Dr. Madhu Viswanatham V; Mr. Annamreddy Dinesh; Mr. Vakkala Shariq Adnan; and Mr. Perugu Ajay Kumar.
The application for the patent was published on Jan. 2, under issue no. 01/2026.
According to the abstract released by the Intellectual Property India: "The present disclosure provides a system for detecting cyberbullying-related hate speech in social media content. The system includes a data preprocessing module configured to receive and process social media text data, a tokenization module configured to convert processed text into numerical feature vectors using TF-IDF techniques, a machine learning module having multiple classification algorithms configured to analyze the numerical feature vectors, and an ensemble classifier module having a Voting Classifier configured to combine predictions from multiple ensemble learning techniques to generate aggregated classification results. The system processes social media datasets through preprocessing operations including data cleaning, label encoding, and oversampling using SMOTE. The machine learning module implements Support Vector Machine, Random Forest, Logistic Regression, Multi-Layer Perceptron with One-vs-One strategy, and Multi-Layer Perceptron with One-vs-Rest strategy algorithms. The ensemble classifier combines Boosted Decision Trees and Bagging Random Forest models to achieve enhanced detection accuracy."
Disclaimer: Curated by HT Syndication.
