A

Project Presentation
on
Fake News Detection using Machine Learning

Shriyesh Srivastava (1509721109)

Pankaj kr. Singh (1509710074)
Revant Tiwari (1509710088)
Guided By
Mr. Sarvanan
A.P. (CSE Dept.)

Department of Computer Science & Engineering

Galgotias College of Engineering & Technology , Greater Noida
Dr. A.P.J. Abdul Kalam Technical University, Lucknow, Uttar Pradesh
Outline

Introduction
Literature Survey
Problem Statement
Methodology
Conclusion
References
 INTRODUCTION
 Fake news on social media has experienced a resurgence of interest due to the
recent political climate and the growing concern around its negative effect.
 Detecting misinformation on social media is an extremely important but also a
technically challenging problem. The difficulty comes in part from the fact that even
the human eye cannot accurately distinguish true from false news.
 In an attempt to combat the growing misinformation and confusion, several fact-
checking websites have been deployed to expose or confirm stories (e.g.
snopes.com).These websites play a crucial role in combating fake news, but they
require expert analysis which inhibits a timely response.
 As a response, numerous articles and blogs have been written to raise public
awareness and provide tips on differentiating truth from falsehood . While each
author provides a different set of signals to look out for, there are several
characteristics that are generally agreed upon, relating to the text of an article, the
response it receives, and its source.
 LITERATURE SURVEY

 BS Detector -
BS Detector is a plug-in used by Mozilla and Chrome browsers to detect the presence
of fake news sources and to alert the user accordingly .It works by searching through
web pages references of links which have already been flagged unreliable in their
database. BS Detector has been used by Facebook to solve their proliferation of fake
news problem.
 Politi Fact -
Politi Fact is a fact-checking US-based website used by editors and writers which give
the credibility of claims by US officials involved American politics. This system places
judgment in the form of Truth-O-Meter which is a measure of the accuracy of a
statement. These people first decide on which news to evaluate
depending upon some characteristics like significance and worthiness of the claim.
After that, the Truth-O-Meter is generated and a panel of more than two people
thoroughly go through it to evaluate final rating of the claim.
 Flock Fake News Detector
Fake News Detector was a feature added by Flock-a new generation messaging and
collaborative platform. Whenever links are being sent to each while chatting, FND
algorithm gets activated. It checks the content of links to their databases of websites
computed according to rankings. It gives a statistic rating and generates a warning
message if the source is not found to be reliable. Flocks database has more than 600
news URL’S that are fact-checked .The drawback of this system is that their database
for fact checking is less in number and chances of hoaxes still not being determined
are high.
 Problem Statement

Fake news is problematic since they can negatively affect the

people. The biggest challenge is the lack of an efficient way to
tell the difference between real news or a fake one, even
humans are often unable to tell the difference. Fake news is a
serious problem, exacerbated by the open nature of the web
and social media in addition to the recent advance in
computer technologies, which simplify the process of creating
and spreading fake news. While it is easier to understand and
trace the intention and the impact of fake reviews, the
intention, and the impact of creating propaganda by
spreading fake news cannot be measured or understood easily.
 Proposed Work

1.Processing the text corpora in which we first convert

each word to tokens according to frequency.

2.Giving each token a vector of uniform length.

3.Padding and truncating the reviews so that they may be

of specific length.

4.length is determined by mean of all the reviews plus 2*

standard deviation .

5.Finally feeding the vectors to the neural networks and

learning the embedding through backpropagation.
Flow Chart
 Accuracy Analysis
S. no Paper/Author Technology used Accuracy
1. Glida, s. et al. NLP(TF-IDF) 77.2%
(evaluating m/c leaning
algorithm for fake news
detection)-2017
2. Granik M. et al. Naïve-Bayes Classifier 74%
(Fake News Detection using
Naïve-Bayes Classifier)-2017
using RNN

3. S. B Parikh et al. Text based Analysis 89%

(Media Rich Fake News
Detection: A Survey)-2018
4. A. Campan et al. Big Data and Analysis 82%
(Fighting Fake News Spread
in Online Social Networks:
Actual trends & future
research directions)-2017
5. S. Singhania et al. 3HAN 86.77%
(3HAN: A deep neural
network for fake news
detection)-2017
Dataset Used:- kaggle.com/account/login?returnUrl=%2ftherohk%2findia-
headlines-news-dataset%2fversion%2f3&login=true#_=_
 References

[1] Allcott, H., And Gentzkow, M., Social Media And Fake News In The
2016 Election.
[2] Signal Media, The Signal Media One-million News Articles Dataset,
Http://Research.Signalmedia.Co/Newsir16/Signal-dataset.Html, URL
Obtained On March 2,2017.
[3] Kaggle, Getting Real About Fake News,
Https://Www.Kaggle.Com/Mrisdal/Fake-news, URL Obtained On March
2, 2017.