MUMBAI, India, Aug. 17 -- Intellectual Property India has published a patent application (202641095644 A) filed by Mohan Babu University on August 07, 2026, for Distributed Stream-Based Sentiment Analysis Framework.
Inventors include Dr. A. V. Sriharsha; Ms. N. Durga Sree; Mr. Pavan Nakka; Ms. N. S. L. Chaitanya Rani; and Ms. C. Kavya.
The application for the patent was published on August 14, 2026, under issue no. 33/2026.
Abstract: The present invention relates to a distributed stream-based sentiment analysis framework and method for simulating real-time processing of textual data using an integrated Extract-Transform-Load (ETL) architecture. The framework comprises a data ingestion module, distributed message streaming platform, stream processing engine, sentiment classification module, cloud-based storage system, visualization module, and performance monitoring mechanism configured to process large-scale textual information in a scalable and fault-tolerant manner. Initially, textual data is acquired from predefined datasets, validated, and transmitted through a distributed messaging platform for continuous stream processing. The stream processing engine preprocesses the incoming data and forwards the processed information to a sentiment classification module that categorizes textual content into positive, negative, or neutral sentiment classes using a natural language processing model. The classified information is subsequently stored within a distributed cloud database, while visualization modules generate analytical representations including sentiment distributions, trend analysis, keyword frequency analysis, and user activity summaries. The framework further monitors throughput, processing latency, storage efficiency, and overall system performance to ensure reliable operation under varying workloads. By eliminating dependence on live social media APIs and integrating distributed ingestion, processing, storage, and visualization into a unified framework, the present invention provides a scalable, reproducible, low-latency, and efficient solution suitable for industrial analytics, business intelligence, academic research, cloud computing, and large-scale social media sentiment analysis.
Disclaimer: Curated by HT Syndication.
