4. Introduction
The Fake News Detection System using MultinomialNB is a
Python Django web project with a SQLite database that
aims to tackle the problem of identifying fake news
articles. The project involves the use of the Multinomial
Naive Bayes algorithm for classifying news articles. The
system is easy to maintain, user-friendly, and can detect
fake news without any human supervision. The project
comprises two major modules, User and Admin, with
various sub-modules, including sign-up, login, news
detection, view results history, edit profile, change
password, and logout for users, and login, dashboard, view
results history, view registered users, change password, and
logout for admins. The system is critical in preventing the
spread of false information, and the project's use of
machine learning techniques ensures that the detection of
fake news is accurate and efficient.
5. Problem Definition
The problem addressed by the Fake News Detection
System project using MultinomialNB is the
proliferation of false information on the internet,
which can lead to negative consequences such as
public panic, mistrust of credible sources, and social
instability. The project aims to develop an automated
system that can distinguish between real news and
fake news using natural language processing and
machine learning techniques. The system will analyze
the text of the news article and determine the
probability of it being true or false. This will help to
prevent the spread of misinformation and protect the
public from being misled.
6. Objective
The objectives of the Fake News Detection System
project using MultinomialNB are:
To develop a machine learning model that can
accurately detect and classify fake news articles.
To create a user-friendly web-based platform for users
to submit news articles for detection and receive
results.
To improve awareness of the prevalence of fake news
and the importance of fact-checking in modern
society.
7. Need of The System
The need for the Fake News Detection System project
using MultinomialNB arises due to the increasing
spread of fake news and misinformation through
social media and other online platforms. The system
aims to address the problem of fake news by
automatically detecting and filtering out false
information from the genuine ones. With the help of
machine learning algorithms such as MultinomialNB,
the system can effectively identify fake news, which
can prevent people from making decisions based on
misleading information. This system is crucial in
maintaining the authenticity of information and can
be used by various industries such as news agencies,
social media platforms, and educational institutions.
8. Purpose
The purpose of the Fake News Detection System using
MultinomialNB is to develop a tool that can
automatically identify fake news from a given news
article. The system aims to tackle the growing problem
of misinformation and fake news, which can cause
significant damage to individuals, society, and
institutions. By using machine learning algorithms like
MultinomialNB, the system can accurately classify
news articles as real or fake based on their content,
language, and other factors. The purpose of this
system is to promote media literacy and encourage
critical thinking while also helping to curb the spread
of fake news.
9. Project Scope
The scope of the Fake News Detection System using
MultinomialNB is vast, as it can be applied in various industries
where the dissemination of false information can cause
significant damage. The system can be used in news agencies,
social media platforms, and other online forums to identify and
prevent the spread of fake news. With the rise of social media
and the ease with which information can be disseminated, it has
become increasingly challenging to distinguish between real and
fake news. This system can provide an effective solution for this
problem and help in maintaining the integrity of information.
The market scope of this system is also significant, as there is a
growing demand for tools that can help in detecting fake news.
The system can be used by media houses, government
organizations, and other institutions that deal with the
dissemination of information to the public. Additionally, the
system can be used as a plugin in web browsers or social media
platforms to provide real-time detection of fake news.
10. Proposed System
The proposed Fake News Detection System using
MultinomialNB is a web-based application that uses a
machine learning algorithm to detect fake news
articles. It has two modules, User and Admin, with
various sub-modules to provide user-friendly
functionality. The system is scalable, robust, and can
be used in various industries, including media,
journalism, and social media platforms. Its benefits
include its ability to automatically identify fake news
and provide an easy-to-use interface for users.
11. User Modules:
Signup: Allows users to create an account by providing
their basic details such as name, email, and password.
Login: Allows registered users to log in to their accounts
using their email and password.
News Detection: Enables users to input news articles or
links and submit them for fake news detection.
View Results History: Allows users to view the results of
the fake news detection analysis performed on the news
articles submitted by them.
Edit Profile: Enables users to update their profile
information such as name, email, and password.
Change Password: Allows users to change their account
password for security purposes.
Logout: Allows users to log out of their accounts and end
their current session.
12. Admin Modules:
Login: The admin can log in to the system using their
credentials.
Dashboard: The admin can view the total number of
registered users and the total number of news articles
that have been analyzed by the system.
View Results History: The admin can view the results
of the news articles that have been analyzed by the
system.
View Registered Users: The admin can view the list of
registered users of the system.
Change Password: The admin can change their login
password.
Logout: The admin can log out of the system.
13. SOFTWARE USED
PYTHON INTERPRETER
PYCHARM IDE (INTEGRATED DEVELOPMENT ENVIRONMENT)
DJANGO FRAMEWORK
NOTEPAD++ OR ANY OTHER TEXT EDITOR
CHROME OR ANY OTHER BROWSER
14. FRONTEND (LANGUAGE USED)
HTML (HYPERTEXT MARKUP LANGUAGE)
CSS (CASCADING STYLE SHEET)
BOOTSTRAP (FRAMEWORK OF HTML,CSS AND JS)
16. SYSTEM DESIGN
Unified Modeling Language:
UML stands for Unified Modeling Language. It is a third
generation method for specifying, visualizing and
documenting the artifacts of an object oriented system
under development. Object modeling is the process by
which the logical objects in the real world (problem space)
are represented (mapped) by the actual objects in the
program (logical or a mini world). This visual
representation of the objects, their relationships and their
structures is for the ease of understanding. This is a step
while developing any product after analysis.
17. The Unified Modeling Language encompasses a
number of models.
Use case diagrams
Class diagrams
Sequence diagrams
18. Use Case Diagram:
Use case diagram consists of use cases and actors and
shows the interaction between them. The key points
are:
The main purpose is to show the interaction between
the use cases and the actor.
To represent the system requirement from user’s
perspective.
The use cases are the functions that are to be
performed in the module.
An actor could be the end-user of the system or an
external system.
19. Use Case Diagrams – Admin :
Admin
Dashboard
View Results History
Manage Reg. Users
(View / Delete)
Change Password
Logout
Admin
20. Use Case Diagrams User:
Edit Profile
(Update)
Change Password
News Detection
View Results History
Logout
User
21. Sequence Diagram:
The purpose of sequence diagram is to show the flow of
functionality through a use case. In other words, we
call it a mapping process in terms of data transfers
from the actor through the corresponding objects.
40. FUTURE SCOPE
The future scope of the Fake News Detection System using
MultinomialNB can include the following:
Incorporating other machine learning models: The system
can be further improved by incorporating other machine
learning models, such as deep learning models, to enhance
its accuracy and efficiency.
Integration with social media platforms: The system can be
integrated with social media platforms to detect and flag
fake news in real-time, thus preventing the spread of
misinformation.
Enhancing the database: The system can be further
improved by expanding its database to include more
sources of news and information, thus enhancing its
accuracy.
Multilingual support: The system can be further enhanced
by adding support for multiple languages, making it more
accessible to a wider audience.
41. FUTURE SCOPE (Continue)
Natural Language Processing (NLP): Integrating NLP
techniques can enhance the accuracy of the system in
detecting fake news, by analyzing the sentiment and
tone of the news articles.
Incorporating multimedia content: The system can be
further improved by incorporating multimedia
content such as images and videos, to detect fake news
that are propagated through such means.
Mobile application: Developing a mobile application
for the system can make it more accessible to users on-
the-go, thus enhancing its usability and user
engagement.
These are just a few of the potential areas for future
development and improvement of the Fake News
Detection System using MultinomialNB.
42. CONCLUSION
In conclusion, the Fake News Detection System using
MultinomialNB is an important tool in the fight against
misinformation and fake news. It uses machine learning
algorithms to classify news articles as either real or fake with a
high degree of accuracy. The system is user-friendly and includes
two major modules, the user module and the admin module.
The user module allows users to sign up, log in, detect news,
view their results history, edit their profile, change their
password, and log out. The admin module allows admins to log
in, view the dashboard, view the results history, view registered
users, change their password, and log out. The system has several
advantages, including its high accuracy in detecting fake news,
user-friendly interface, and easy maintenance. However, the
system's limitations include its reliance on the quality of the
training data and the possibility of misclassifying news articles
due to their similarity to real news articles. Overall, the Fake
News Detection System using MultinomialNB has great
potential in combating the spread of fake news and
misinformation, and its future scope includes the integration of
more advanced machine learning algorithms and techniques.
43. BIBLIOGRAPHY
FOR PYTHON INSTALLATION
https://www.python.org
FOR HTML , CSS AND PYTHON BASICS
www.w3schools.com
www.javatpoint.com
https://www.geeksforgeeks.org/python-django/
https://panjwanitutorials.com/
REFERENCE BOOKS
Two scoops of Django for 1.11 by Daniel Greenfeld’s and Audrey
Greenfield
Lightweight Django by Elman and Mark Lavin