Reducing Fraudulent News Proliferation using Classification Techniques
A Raghuvira Pratap1, Prasad J V D2, Sallagundla Babu3 , V V N V Phani Kumar4
1A Raghuvira Pratap*, Department of Computer Science and Engineering, V.R.Siddhartha Engineering College,Andhra Pradesh, Vijayawada, India.
2Prasad J V D , Department of Computer Science and Engineering, V.R.Siddhartha Engineering College, Andhra Pradesh, Vijayawada, India.
3Sallagundla Babu, Department of Computer Science and Engineering, V.R.Siddhartha Engineering College,Andhra Pradesh, Vijayawada, India.
4V V N V Phani Kumar, Department of Computer Science and Engineering, V.R.Siddhartha Engineering College,Andhra Pradesh, Vijayawada, India.
Manuscript received on January 26, 2020. | Revised Manuscript received on February 05, 2020. | Manuscript published on February 30, 2020. | PP: 3362-3365 | Volume-9 Issue-3, February 2020. | Retrieval Number: C6022029320/2020©BEIESP | DOI: 10.35940/ijeat.C6022.029320
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: The expansion of dishonorable information in normal get entry to social access media retailers like internet based media channels, news web journals, and online papers have made it hard to identify dependable news sources, subsequently growing the need for technique tools able to deliver insights into the reliability of online content substances.. This paper comes up with the applications of Natural language process techniques for detective work the dishonest news, that is, dishonorable news stories that return from the non-reputable sources. Solely by building a model supported mistreatment word tallies or a Term Frequency-Inverse Document Frequency matrix, will solely get you to date. Is it potential for you to make a model which will differentiate between “Real “news and “Fake” news? Thus our planned work is going to be on grouping a knowledge set of each pretend and real news and uses a Naïve mathematician classifier so as to make a model to classify an editorial into pretend or really supported its words and phrases.
Keywords: Fraudulent, Fake News, Natural language processing, TF-IDF, Fake News.