Rumor Detection
Yogesh J. Bhosale1, Mayuresh B. Kedari2, Tejas V. Tarawade3, Abhishek S. Late4
1Yogesh Bhosale, Department of Computer Science Indira College of Engineering and Management, Pune (Maharashtra), India.
2Mayuresh Kedari, Department of Computer Science, Indira College of Engineering and Management, Pune (Maharashtra), India.
3Tejas Tarawade*, Department of Computer Science Indira College of Engineering and Management, Pune (Maharashtra), India.
4Abhishek Late, Department of Computer Science Indira College of Engineering And Management, Pune (Maharashtra), India.
Manuscript received on June 06, 2021. | Revised Manuscript received on June 13, 2021. | Manuscript published on July 30, 2021. | PP: 14-16 | Volume-10 Issue-2, July 2021. | Retrieval Number: 100.1/ijrte.B60730710221| DOI: 10.35940/ijrte.B6073.0710221
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Everyone has internet access and is connected to social media in today’s fast-paced world. Numerous pieces of data are disseminated on these websites, but there is no reliable source for confirmation or verification. This is where rumors come into play. Rumors are deliberate fabrications intended to sway or drastically alter popular opinion, and their impact can be seen in politics, especially during elections, and on social media. Thus, to resolve this problem, a rumor detector is needed that is capable of accurately indicating whether information is false or real. We implemented algorithms such as Multinomial Naive Bayes, Gradient Boosting, and Random Forest on complex datasets to get this Rumor Detection System closer to more reliable rumor performance. Accuracy of Multinomial Naive Bayes is approximately 90.4Forestitwas86.588.3.
Keywords: Rumor, Fake News, Prediction, Detection Naïve Bayes’ classifier, Machine Learning Application.