MUMBAI, India, June 26 -- Intellectual Property India has published a patent application (202631070571 A) filed by Kalinga Institute Of Industrial Technology Kiit Deemed To Be University on June 05, 2026, for Method Of Detecting Online Misinformation Using Machine Learning Classification.
Inventors include Dey, Raghunath; and Piri, Jayashree.
The application for the patent was published on June 19, 2026, under issue no. 25/2026.
Abstract: A computer-implemented method of detecting online misinformation includes receiving a text dataset (102) containing news content and preprocessing the text dataset to convert the text dataset into a processed text dataset. The preprocessing includes performing stopword removal, stemming, tokenization, punctuation removal, and missing values removal. The method further includes extracting features from the processed text dataset using Term Frequency-Inverse Document Frequency (TF-IDF) vectorization (106) to generate numerical feature representations that quantify importance of words within the text dataset. One or more machine learning classifiers (108) are trained using the numerical feature representations, where the one or more machine learning classifiers include at least one of a logistic regression classifier, a decision tree classifier, or a support vector machine classifier. The news content is classified as genuine or fraudulent based on output from the one or more trained machine learning classifiers. (FIG. 1)
Disclaimer: Curated by HT Syndication.
