You are on page 1of 8

Determining Fake Statements made by Public

Figures by means of Artificial Intelligence


A PROJECT REPORT

Submitted in fulfilment for the award of Degree of Bachelor of Technology


in
COMPUTER SCIENCE AND ENGINEERING

Submitted
By

Y.S.K Yogesh Reddy 15951A05P3


Vaishnavi Mogalighidha 15951A05L9
Vinay Tamtam 15951A05N6
Suryateja Kudupudi 15951A05K7

Under the Supervision


Of
Dr. J Shirisha Devi
Professor, CSE

INSTITUTE OF AERONAUTICAL ENGINEERING


(Autonomous)
Dundigal – 500043, Hyderabad, Telangana
2018-2019
INSTITUTE OF AERONAUTICAL ENGINEERING
(Autonomous)
Dundigal, Hyderabad - 500043, Telangana.

COMPUTER SCIENCE AND ENGINEERING

CERTIFICATE

This is to certify that work embodied in this dissertation entitled “Determining


Fake Statements made by Public Figure by means of Artificial Intelligence”
being submitted by
Y.S.K Yogesh Reddy 15951A05P3
Vaishnavi Mogalighidha 15951A05L9
Vinay Tantam 15951A05N6
Suryateja Kudupidi 15951A05K7

for partial fulfilment of the requirement for the award of ‘Bachelor of


Technology’ in ‘Computer Science and Engineering’ discipline to Institute of
Aeronautical Engineering, Dundigal, Hyderabad during the academic year
2018-2019 as a record of bonafide piece of work, undertaken by her
supervision of the undersigned.

Supervised by Head of the Department


Dr. J Shirisha Devi Dr. M Madhu Bala
Professor, CSE Professor, CSE

EXTERNAL EXAMINER

I
INSTITUTE OF AERONAUTICAL ENGINEERING
(Autonomous)
Dundigal, Hyderabad - 500043, Telangana

COMPUTER SCIENCE AND ENGINEERING

DECLARATION

We the students of Bachelor of Technology in Computer Science and


Engineering, 2018 - 2019, Institute of Aeronautical Engineering, Dundigal,
Hyderabad, hereby declare that the work presented in this project work entitled
“Determining Fake Statements made by Public Figures by means of
Artificial Intelligence” is the outcome of our own bonafide work and is correct
to the best of our knowledge. This work follows engineering ethics and contains
no material previously published or written by neither person nor material which
has been accepted for the award of any other degree or diploma of the university
or other institute of higher learning, except where due acknowledgement has
been made in the text.

Y. S.K Yogesh Reddy 15951A05P3


Vaishnavi Mogalighidha 15951A05L9
Vinay Tamtam 15951A05N6
Suryateja Kudupudi 15951A05K7

Date:

II
ACKNOWLEDGEMENT

The satisfaction that accompanies the successful completion of any task would
be incomplete without the mention of the people who made it possible and
whole constant guidance and encouragement crown all the efforts with success.
We thank our college management and respected Sri M. Rajashekar Reddy,
Chairman, IARE, Dundigal for providing us the necessary infrastructure to carry
out the project work.

We express our sincere thanks to Dr. L.V. Narasimha Prasad, Professor,


Principal, and who has been a great source of information for our work, and Dr.
M Madhu Bala, Professor and Head of the CSE department, for extending her
support to carry on this project work.

We are especially thankful to our internal supervisor Dr. J Shirisha Devi,


Professor and Head of the department, CSE, for her internal support and
professionalism who helped us in shaping the project into successful one.

We take this opportunity to express our thanks to one and all who directly or
indirectly helped us in bringing this effort to present form.

III
ABSTRACT
This project shows an approach for detecting fake statements made by public Figure by
means of artificial intelligence. Several approaches were implemented as a software system
and tested against a data set of statements. The best achieved result in binary classification
problem (true or false statement) is 86%. The results may be improved in several ways that
are described in the article as well. The news information that we get is not always true. The
internet makes it harder to fact check the available information, because there are too many
sources that often even contradict each other. All of this caused the emergence of fake news.
Mass media and social media have a great influence on a public. There are sides that are
interested in using this to achieve their political goals with the help of fake news. They
provide false information in form of news to manipulate people in different ways. There exist
lots of websites with a single purpose of spreading of false information. In existing method,
Classification is done by supervised machine learning models and neural networks. Only the
statements themselves are used for classification purposes. This means that none of the meta
data provided is used for classification Whereas in proposed system, the meta data is included
in training process. Data set scale is increased by augmenting extensive data. Model can be
improved tuning the trained model.

IV
TABLE OF CONTENTS

1. INTRODUCTION
1.1 OVERVIEW 1
1.2 EXISTING SYSTEM 2
1.2.1 FUNCTIONALITY
1.2.2 DRAWBACKS
1.3 PROPOSED SYSTEM 2
1.3.1 FUNCTIONALITY
1.3.2 ADVANTAGES
1.4 PROBLEM STATEMENT 3
2. LITERATURE SURVEY 4
3. SYSTEM ANALYSIS
3.1 PROCESS MODEL USED WITH JUSTIFICATION 7
3.2 UML DIAGRAMS 13
3.2.1 USE CASE DIAGRAM 17
3.2.2 SEQUENCE DIAGRAM 18
3.2.3 COLLABORATION DIAGRAM 19
3.2.4 STATE CHART DIAGRAM 20
3.2.5 ACTIVITY DIAGRAM 21
3.2.6 COMPONENT DIAGRAM 22
3.2.7 DEPLOYMENT DIAGRAM 22
3.3 ALGORITHMS 23
4. FEASIBILITY STUDY 30
4.1 ECONOMICAL FEASIBILITY
4.2 TECHNICAL FEASIBILITY
4.3 SOCIAL FEASIBILITY
5. SOFTWARE REQUIREMENT SPECIFICATION
5.1 FUNCTIONAL REQUIREMENTS 31
5.2 NON FUNCTIONAL REQUIREMENTS 33
5.3 SOFTWARE REQUIREMENTS 33
5.4 HARDWARE REQUIREMENTS 33

V
6. IMPLEMENTATION
6.1 SOFTWARE ENVIRONMENT 34
6.2 SAMPLE CODE
7. RESULTS 38
8. SYSTEM TESTING 42
9. CONCLUSION
9.1 CONCLUSION 49
9.2 FUTURE SCOPE 49
10.REFERENCES 50

VI
LIST OF FIGURES

Figure 3.1 Spiral Model 7


Figure 3.2 Requirement Definition Stage 8
Figure 3.3 Design Stage 9
Figure 3.4 Development Stage 10
Figure 3.5 Integrattion and Test Stage 11
Figure 3.6 Installation and Acceptance Stage 12
Figure 3.7 Use Case Diagrams 17
Figure 3.8 Sequence Diagrams 19
Figure 3.9 Collaboration Diagram 19
Figure 3.10 State Chart Diagram 20
Figure 3.11 Activity Diagram 21
Figure 3.12 Component Diagram 22
Figure 3.13 Development Diagram 22
Figure 3.14 Multi Layer Perceptron 23
Figure 3.15 Random Forest 24
Figure 3.16 Logistic Regresion 26
Figure 3.17 Support Vector Machines 28
Figure 5.1 Functional Requirements 31
Figure 6.1 Sample Code 1 36
Figure 6.2 Sample Code 2 37
Figure 6.3 Sample Code 3 37
Figure 7.1 Admin Login Page 38
Figure 7.2 Detecting Fake Statements 38
Figure 7.3 Data Set 39
Figure 7.4 Uploading Data set 39
Figure 7.5 Classification 40
Figure 7.6 Classification using Test Data 40
Figure 7.7 Bar Graph 41
Figure 8.1 Levels of Testing 43

VII

You might also like