The significance of social media has increased manifold in the past fewdecades as it helps people from even the most remote corners of the world to stay connected . With the advent of technology, digital media has become morerelevant and widely used than ever before . Along with this, there has been aresurgence in the circulation of fake news and tweets that demand immediate attention . In this paper, we describe a novel Fake News Detection system thatautomatically identifies whether a news item is “real” or “fake” We have used an ensemble model consisting of pre-trained models followeded by a statistical feature fusion network, along with a novel heuristical algorithm by incorporating various attributes present in news items or tweets like source, username handles, URL domains and authors as statistical feature . We obtained a bestF1-score of 0.9892 on the COVID-19 dataset, and an F1- Score of 0 .9073 on the FakeNewsNet dataset. We have also quantified reliable predictive uncertaintyalong with

Author(s) : Sourya Dipta Das, Ayan Basak, Saikat Dutta

Links : PDF - Abstract

Code :

https://github.com/oktantod/RoboND-DeepLearning-Project


Coursera

Keywords : news - fake - tweets - statistical - score -

Leave a Reply

Your email address will not be published. Required fields are marked *