Logo

Certain Investigation of Fake News Detection from Facebook and Twitter Using Artificial Intelligence Approach

Setiawan, Roy and Ponnam, Vidya Sagar and Sengan, Sudhakar and Anam, Mamoona and Subbiah, Chidambaram and Phasinam, Khongdet and Vairaven, Manikandan and Ponnusamy, Selvakumar (2021) Certain Investigation of Fake News Detection from Facebook and Twitter Using Artificial Intelligence Approach. [UNSPECIFIED]

[img] PDF
Download (3418Kb)
    [img] PDF
    Download (6Mb)

      Abstract

      The news platform has moved from traditional newspapers to online communities in the technologically advanced area of Artificial Intelligence. Because Twitter and Facebook allow us to consume news much faster and with less restricted editing, false information continues to spread at an impressive rate and volume. Online Fake News Detection is a promising feld in research and captivates the attention of researchers. The sprawl of huge chunks of misinformation in social network platforms is vulnerable to global risk. This article recommends using a Machine Learning optimization technique for automated news article classification on Facebook and Twitter. The emergence of the research is facilitated by the strategic implementation of Natural Language Processing for social forum fake news findings in order to distort news reports from non-recurrent outlets. The relent from the study is outstanding with text document frequency words, which act as extraction technique�s attribute, and the classifier is acted upon by Hybrid Support Vector Machine by achieving 91.23% accuracy.

      Item Type: UNSPECIFIED
      Uncontrolled Keywords: NLP � Hybrid SVM � Machine Learning � Fake News
      Subjects: H Social Sciences > HD Industries. Land use. Labor > HD28 Management. Industrial Management
      Divisions: Faculty of Economic > Business Management Program
      Depositing User: Admin
      Date Deposited: 23 Nov 2022 21:08
      Last Modified: 27 Dec 2022 17:15
      URI: https://repository.petra.ac.id/id/eprint/19818

      Actions (login required)

      View Item