Fake News Identification and Analysis Study on ISOT Dataset using Machine Learning Classifiers


Vikas Sejwar, Abhilash Sonker
Madhav Institute of Technology & Gwalior, India.


The spreading usability of online media, mostly persons has changed the mode news accessibility. Online news has come to be a major birthplace of data for public. Though, more data emerges on the online networks is appealing and anticipated to misinform. Many wrong information’s are exact similar to tangible ones that it is challenging for a person to see himself. Therefore, preset counterfeit detection implements like learning techniques have come to be a necessary prerequisite. In this paper, we have examined the activity of learning classifier in both false and real ISOT data sets of different sizes have the opposite assurance. We evaluated different classifiers like as LR, SVM, k-NN, DT, RF and review of other enhanced learning techniques on different datasets. In order to test the presentation of the models, we select precision, accuracy, recall and F1-score as test metrics to determine models performance. After that, we reviewed and analyzed many approaches that got accuracy on ISOT fake news dataset. Keywords- Machine learning models, False and Real ISOT dataset.