MUMBAI, India, Jan. 9 -- Intellectual Property India has published a patent application (202511113857 A) filed by Ravi Pal; and Dr. Shiva Prakash, Gorakhpur, Uttar Pradesh, on Nov. 19, 2025, for 'fake review detection for multilingual low resource languages( hindi, urdu and bengali ) using machine learning techniques.'
Inventor(s) include Ravi Pal; and Dr. Shiva Prakash.
The application for the patent was published on Jan. 9, under issue no. 02/2026.
According to the abstract released by the Intellectual Property India: "The widespread dissemination of misinformation across various languages and domains on social media platforms presents a substantial societal risk. Current automated detection approaches for low-resource languages are constrained by two factors: the sequential length limitations inherent in pre-trained language models such as multilingual bidirectional encoder representations from transformers, and the existence of noisy training data. In the contemporary global digital environment, misinformation surpasses linguistic barriers, presenting a substantial challenge for moderation systems. Although substantial progress has been achieved in misinformation detection, the emphasis continues to be primarily on monolingual high-resource environments, with low-resource languages frequently neglected. This survey seeks to address that lacuna by offering a comprehensive overview of the existing research on misinformation detection in low-resource languages within both monolingual and multilingual contexts. This research presents a multilingual false news detection system employing machine-learning techniques."
Disclaimer: Curated by HT Syndication.
