FAKE NEWS DETECTION USING MULTI-

PERCEPTRON ALGORITHM
A PROJECT REPORT

Submitted By
AHMED SHALIH S
BADRINATH M H
DARWIN PANDIA RAJ V
HARI LINGESHWARAN K
In partial fulfillment for the award of the degree

Of

BACHELOR OF ENGINEERING
IN
COMPUTER SCIENCE AND ENGINEERING

CHRISTIAN COLLEGE OF ENGINEERING AND TECHNOLOGY,

ODDANCHATRAM – 624 619
ANNA UNIVERSITY::CHENNAI 600 025

MAY 2023
 ANNA UNIVERSITY:: CHENNAI 600 025

BONAFIDE CERTIFICATE
Certified that this Thesis titled “FAKE NEWS DETECTION USING
MULTI-PERCEPTRON ALGORITHM” is the bonafide work of
"BADRINATH.M.H(920319104004), DARWIN PANDIA RAJ.V
(920319104005), AHMED SHALIH.S(920319104001), HARI
LINGESHWARAN.K (920319005008)” who carried out the project work
under my supervision.

SIGNATURE SIGNATURE
Dr.C.SUNDAR,M.E.,Ph.D, Dr.C.SUNDAR,M.E.,Ph.D,

HEAD OF THE DEPARTMENT, HEAD OF THE DEPARTMENT,

Christian College of Engg & Tech, Christian College of Engg & Tech,
Oddanchatram-623619 Oddanchatram-623619

Submitted for the university viva-voice examination held on.........................

INTERNAL EXAMINER EXTERNAL EXAMINER

II
 ACKNOWLEDGEMENT
We thank the most graceful creator of the universe, our almighty GOD
who ideally supported us throughout this project.

At this moment of having successfully completed our project, we wish to

convey our sincere thanks to the management for providing all the facilities to
us.

We would like to express our sincere thanks to our principal

Dr.THARCIS, M.E., Ph.D., for letting us to do our project and offering
adequate duration in completing our project.

We would like to express our gratitude to our Head of Department of

Computer Science And Engineering, Dr. C. SUNDAR, M.E., Ph.D., for his
constructive suggestions during our project.

With deep sense of gratitude, we extend our sincere thanks to our project
guide Dr. C. SUNDAR, M.E., Ph.D., Head Of The Department, Department of
Computer Science And Engineering, who is our light house in the vast ocean of
learning with her inspiring guidance & encouragement to complete the project.

We would like to express our gratitude to our project coordinator by

Mrs.ROY SUDHA REETHA, , M.E.,MISTE.,(Ph.D)., Assistant Professor,
Department of Information Technology for her valuable support throughout the
project.

Finally we also offer our thanks to all teaching and non –teaching staff
members of Information Technology department and our friends for their kind
help extended to us
AHMED SHALIH S
BADRINATH M H
DARWIN PANDIA RAJ V
HARI LINGESHWARAN K

III
 ABSTRACT
Internet is one of the important inventions and a large number of persons
are its users. These persons use this for different purposes. There are different
social media platforms that are accessible to these users. Any user can make a
post or spread the news through these online platforms. FAKE news has
proliferated to a big crowd than before in this digital era, the main factor derives
from the rise of social media and direct messaging platform. Fake news
detection is important research to be done for its detection but it has some
challenges too. Some challenges can be due to a smaller number of resources
like an available dataset. We propose in this project, a fake news detection using
deep learning technique. And implement a novel automatic fake news
credibility inference model using deep learning algorithm with Natural language
processing steps which including text mining steps. Based on a set of explicit
and latent features extracted from the textual information, deep learning
algorithms builds a deep diffusive network model to learn the representations of
news articles, creators and subjects simultaneously. There is a Kaggle
competition called as the “Fake News Challenge” and social network is
employing AI to filter fake news stories out of users’ feeds. Combatting the fake
news is a classic text classification project with a straight forward proposition.
And evaluate the performance of the system in terms of accuracy parameter.

IV
 TABLE OF CONTENTS
CHAPTER TOPIC PAGE NO
NO
ABSTRACT IV
LIST OF FIGURES VIII
LIST OF ABBREVATIONS IX
1 INTRODUCTION 1
1.1 Fake News Classification 1
1.2 Deep Learning 2
1.3 Applications Of Deep Learning 3
1.4 Deep Learning Works 4
1.5 Predictive Analysis 6
1.6 Machine Learning 8
1.7 Artificial Intelligence 10
1.8 Reinforcement Learning 12

2 LITERATURE SURVEY 15

3 EXISITNG SYSTEM 19
3.1 Conventional Classifiers 19
3.1.1 Random Forest Algorithm 19
3.1.2 Navies Bayes Algorithm 21
3.2 Challenges 22
3.3 Disadvantages 23
4. PROPOSED SYSTEM 24
4.1 Multi-Layer Perceptron Algorithm 24
4.2 Advantages 26
4.3 Applications 26
4.4 DIFFERENCE BETWEEN EXISTING 27
AND PROPOSED SYSTEM
5. SYSTEM DESIGN 29
V
 5.1 System Architecture 29
5.2 Modules 30
5.2.1 Train The Documents 30
5.2.2 Text Mining 30

5.2.3 Document Term Matrix Construction 31

5.2.4 Classification 32
5.2.5 Fake News Detection: 33
6. SYSTEM SPECIFICATIONS 34
6.1 Hardware Specification 34
6.2 Software Requirements 34
6.3 Software Description 35
6.3.1 Scikit Learn 40
6.3.2 Matplotlib 42
7 SYSTEM TESTING 43
7.1 Testing 43
7.1.1 Overview Of Testing 44
7.2 Testing Methods 45
7.2.1 Static Vs. Dynamic Testing 45
7.2.2 White-Box Testing 45
7.2.3 Static Testing Methods 46
7.2.4 Black-Box Testing 46
7.2.5 Grey-Box Testing 47
7.3 Testing Levels 49
7.3.1 Unit Testing 49
7.3.2 Integration Testing 50
7.3.3 System Testing 50
7.3.4 Acceptance Testing 50

VI
 7.4 Testing Approaches 50
7.4.1 Bottom-Up 50
7.4.2 Top-Down 51
7.5 Objectives Of Testing 51
7.5.1 Installation Testing 51
7.5.2 Compatibility Testing 51
7.5.3 Smoke And Sanity Testing 52

7.5.4 Regression Testing 52

7.5.5 Alpha Testing 52
7.5.6 Beta Testing 52
7.5.7 Functional Vs Non-Functional Testing 53
7.5.8 Destructive Testing 53
7.5.9 Software Performance Testing 53
7.5.10 Usability Testing 54
7.5.11 Accessibility Testing 54
7.5.12 Security Testing 54
7.5.13 Development Testing 54
8 CONCLUSION AND FUTURE 55
ENHANCEMENT
8.1 Conclusion 55
8.2 Future Enhancement 55
APPENDIX 56
A1 CODING 56
A2 SCREENSHOT 62
REFERENCES 68

VII
 LIST OF FIGURES
FIGURE FIGURE NAME PAGE NO
NO
4.1 Mlp Algorithm 26
5.1 System Architecture 29

6.1 Python Logo 36

A2.1 IDE 62

A2.2 Matrix 65

A2.3 Web Application Link 66

A2.4 Web Application 66

A2.5 Detecting Fake News 67

A2.6 Prediction Output 67

VIII
 LIST OF ABREVIATION
A2C - Synchronous Advantage Actor-Critic
ANN - Artificial Neural Network
BOW - Bag of Words
CNN - Convolutional Neural Network
COPD - Chronic Obstructive Pulmonary Disease
DDPG - Deep Deterministic Policy Gradient
DNN - Deep Neural network
DQN - Deep Q-Network
ECU - Electronic Control Unit
FNC - Federal Networking Council
FPGA - Field Programmable Gate Array
LSTM - Long Short-Term Memory
MLP - Multilayer Perceptron Algorithm
NLP - Natural Language Processing
SNL - Stanford Natural Language
SVM - Support Vector Machine
SVM - Support Vector Machine
TF-IDF - Term Frequency-Inverse Document Frequency
UCLA - University of California, Los Angeles

IX