MUMBAI, India, July 11 -- Intellectual Property India has published a patent application (202541060945 A) filed by MLR Institute of Technology, Hyderabad, India, on June 26, for 'method to public sentiment analysis using gaining-sharing knowledge optimization technique with double path transformer network approach.'

Inventor(s) include Dr. Venkata Nagaraju Thatha; Mr. B. Veerasekharreddy; Mrs. J. Adilakshmi; and Mrs. S. Viharika.

The application for the patent was published on July 11, under issue no. 28/2025.

According to the abstract released by the Intellectual Property India: "Sentiment Analysis (SA) is an important area in natural language processing invention due to its considerable significance in understanding public opinions and executing exact opinion-based evaluations. A wide variety of data kinds, including pictures, videos, music, and text, are constantly flooding in due to the proliferation of online shopping and social media usage. Particularly important for inventors to pay close attention to is text, which is the most important type of unstructured data. Several approaches have been suggested to efficiently extract useful information from large datasets, which is understandable given the data's abundance. Recognizing polarity in lengthy consumer reviews is still a challenge because of the complexities of dealing with massive textual datasets generated by reviews, comments, tweets, and postings. In response to this difficulty, this research presents the Double Path Transformer Network (DPTN), an easy-to-understand architecture that models both global and local information for thorough review classification. The research suggests a parallel design that mixes a convolutional network with a strong self-attention mechanism to improve the attention path's synergy with the convolutional path. The hyper parameters are fine-tuned using the gaining-sharing knowledge optimization (GSK) method, which improves the classification accuracy of the model. Even without clear metrics for class imbalances, the research shows that optimization techniques and deep learning work together to control them finessefully."

Disclaimer: Curated by HT Syndication.