Imbwaga, J.L.Chittaragi, N.Koolagudi, S.G.2026-02-062022ACM International Conference Proceeding Series, 2022, Vol., , p. 271-27521531633https://doi.org/10.1145/3549206.3549256https://idr.nitk.ac.in/handle/123456789/29738There has been an exponential growth in users sharing news and information in real-time on various social media platforms worldwide. However, few of the users share fake and misleading news for various reasons. The reasons for sharing fake news may not be limited to financial, personal, and/or political gain. Since users cannot determine or censor the type of content that appears on their respective platforms, fake news can pose significant and detrimental effects on an individual and society at large. In this regard, we have proposed the work with the primary objective of development of a fake news detection system by applying supervised machine learning algorithms on an annotated (labeled) dataset. The dataset was selected from Kaggle, consisting of fake news with 23503 entries and true news with 21418 entries. An overall better accuracies are observed with tree-based decision tree classifiers and a gradient boosting ensemble algorithm. © 2022 ACM.Fake News DetectionGradient BoostingRandom ForestTerm Frequency and Inverse document frequency