SVS GROUP OF INSTITUTIONS
DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING
BATCH: 2022-2026
MINI PROJECT
FAKE NEWS DETECTOR
Submitted to JAWAHARLAL NEHRU TECHNOLOGY
UNIVERSITY, HYDERABAD
In partial fulfilment of the requirement for the award of
degree of ONLINE BACHELOR OF TECHNOLOGY IN
COMPUTER SCIENCE AND ENGINEERING
Under the guidance of:
TEAM MEMBERS: CH.Sharath
Ponna Pravalika-22TK1A0589 Assistant Professor
Shaguftha Naaz-22TK1A0598
Thota Komalatha-22TK1A05A5
FAKE
NEWS
DETECTOR
ABSTARCT
• IN RECENT YEARS, DUE TO THE BOOMING DEVELOPMENT OF ONLINE SOCIAL
NETWORKS, FAKE NEWS FOR VARIOUS COMMERCIAL AND POLITICAL PURPOSES
HAS BEEN APPEARING IN LARGE NUMBERS AND WIDESPREAD IN THE ONLINE
WORLD. WITH DECEPTIVE WORDS, ONLINE SOCIAL NETWORK USERS CAN GET
INFECTED BY THIS ONLINE FAKE NEWS EASILY, WHICH HAS BROUGHT ABOUT
TREMENDOUS EFFECTS ON THE OFFLINE SOCIETY ALREADY. AN IMPORTANT
GOAL IN IMPROVING THE TRUSTWORTHINESS OF INFORMATION IN ONLINE
SOCIAL NETWORKS IS TO IDENTIFY THE FAKE NEWS TIMELY. THIS PAPER AIMS AT
INVESTIGATING THE PRINCIPLES, METHODOLOGIES AND ALGORITHMS FOR
DETECTING FAKE NEWS ARTICLES, CREATORS AND SUBJECTS FROM ONLINE
SOCIAL NETWORKS AND EVALUATING THE CORRESPONDING PERFORMANCE.
INFORMATION PRECISENESS ON INTERNET, ESPECIALLY ON SOCIAL MEDIA, IS AN
INCREASINGLY IMPORTANT CONCERN, BUT WEB-SCALE DATA HAMPERS, ABILITY
TO IDENTIFY, EVALUATE AND CORRECT SUCH DATA, OR SO CALLED "FAKE
NEWS," PRESENT IN THESE PLATFORMS. IN THIS PAPER, WE PROPOSE A
METHOD FOR "FAKE NEWS" DETECTION AND WAYS TO APPLY IT ON FACEBOOK,
ONE OF THE MOST POPULAR ONLINE SOCIAL MEDIA PLATFORMS. THIS METHOD
USES NAIVE BAYES CLASSIFICATION MODEL TO PREDICT WHETHER A POST ON
FACEBOOK WILL BE LABELED AS REAL OR FAKE. THE RESULTS MAY BE
IMPROVED BY APPLYING SEVERAL TECHNIQUES THAT ARE DISCUSSED IN THE
PAPER. RECEIVED RESULTS SUGGEST, THAT FAKE NEWS DETECTION PROBLEM
CAN BE ADDRESSED WITH MACHINE LEARNING METHODS.
CONTENTS
1.Introduction
2.Problem Statement
3.Existing System
4.Proposed System
5.Architecture
6.System requirements
7.Dataset
8.Algorithms Used
9.System Implementation
10.Output Screenshots
11.Conclusion
12.Future Scope
INTRODUCTION
▶ Fake news detection has become an important
task in today's world. This project aims to
automatically detect whether a news article is
real or fake using Machine Learning
Importance of Fake News Detection:
01 Combat Misinformation Reduces the
spread of false narratives among the
public.
02 Strengthen Democracy Empowers
informed decision-making and enhances
civic participation.
03 Promote Credibility Encourages
trusted sources and responsible
journalism practices.
04 Enhance Digital Literacy Helps
individuals critically evaluate online
information and sources
TYPES OF FAKE NEWS:
> Satirical Comedic stories that mimic
real news but are intended solely for
entertainment purposes and
mislead readers.
>Misleading Information presented in
a deceptive way to support a
specific agenda, often twisting facts
or quotes.
> Hoaxes Fake news crafted to
provoke outrage or confusion, often
going viral and causing significant
misinformation spread.
PROBLEM STATEMENT
▶ The widespread circulation of fake
news on digital platforms poses a
serious threat to society by spreading
misinformation. This project aims to
develop a machine learning-based
Fake News Detector that classifies
news articles as real or fake by
analyzing their textual content using
Natural Language Processing
techniques and supervised learning
models.
EXISTING SYSTEM
Traditional news verification
depends on fact-checkers and
human effort. This is slow and
cannot handle large-scale data.
PROPOSED SYSTEM
In this project, we propose an ML-based solution
using supervised learning where the model is
trained to classify the news content as either real
or fake using the Logistic Regression, Naïve
Bayes and Support Vector Machine algorithms.
ADVANTAGES
>Increased Trust in Media Sources:
Effective fake news detection helps maintain public trust in
media outlets and journalists
>Promotion of Critical Thinking:
The ability to identify fake news encourages individuals to
think critically about the information they encounter online
>Prevention of Manipulation:
By exposing fake news, we can prevent malicious actors
from using misinformation to manipulate public opinion or
influence political processes
>Protection from Harmful Misinformation:
Fake news can have serious consequences, including the
spread of conspiracy theories, the erosion of social
cohesion, and the undermining of democratic processes.
>Improved Social Cohesion:
Identifying and addressing fake news helps to maintain a
healthy and informed public discourse
DISADVANTAGES
The rapid spread of Fake News and disinformation can
have profound consequences. Examples include:
• Distrust in the media
• Undermining the democratic process
• Platforms for harmful conspiracy theories and hate speech
• Spread of false or discredited science – e.g. anti-vax movement
• Reinforcing unhelpful biases
• Threatening access to unbiased, substantiated information
MODULES
•IN THIS PROJECT, I HAVE USED 2
MODULES WHICH ARE LISTED BELOW:
• ✅PYTHON BACKEND MODULES
• ✅ FRONTEND TECHNOLOGIES
SYSTEM
ARCHITECTURE
SYSTEM REQUIREMENTS
Hardware Requirements:
Component Specification
Minimum Intel i3 10th
Processor===== Gen / Ryzen 3 or
higher
Minimum 4 GB
RAM========
(Recommended 8 GB)
1 GB free (dataset +
Storage=====
code + libraries)
GPU======= Not required
64-bit OS (Windows
System Type==
10/11)
Required for dataset
Internet==== download & package
installation
SYSTEM REQUIREMENTS
Software Requirements:
Software Version
Windows 10/11 64-
Operating System
bit
3.10.x or 3.11.x (you
Python========
used around 3.11
earlier)
Pip==========
Latest version
=
VSCode (with Live
IDE========= Server extension
installed)
Google Chrome /
Browser=====
Edge
Dataset Files=== Fake.csv, Real.csv
pandas, numpy,
scikit-learn, flask,
Python Packages
flask-cors, pickle
(builtin)
DATASET DESCRIPTION
•Fake.csv → 23481 fake news articles
•Real.csv → 21417 real news articles
•Column Used: text
ALGORITHMS USED:
• LOGISTIC REGRESSION:
A BINARY CLASSIFICATION ALGORITHM THAT PREDICTS ONE
OF TWO CLASSES — REAL OR FAKE.
• NAÏVE BAYES:
SUPERVISED LEARNING ALGORITHM BASED ON
PROBABILISTIC CLASSIFICATION TECHNIQUE.
• SUPPORT VECTOR MACHINE:
SUPERVISED LEARNING METHODS USED FOR
CLASSIFICATION, AND REGRESSION.
SYSTEM IMPLEMENTATION
• TECHNOLOGIES USED
• FRONTEND: HTML,CSS, JAVASCRIPT
• BACKEND: PYTHON, FLASK
• ML MODELS: NAIVE BAYES, SVM, LOGISTIC REGRESSION (SCIKIT-LEARN)
• TEXT PROCESSING: COUNTVECTORIZER
• DATA: FAKE.CSV, TRUE.CSV
SYSTEM IMPLEMENTATION
Modules
•Preprocessing: Cleans text, creates title, text, and combined inputs
•Model Training: Trains 3 ML models and saves .pkl files
•Flask App: Takes input, predicts Fake/Real, returns confidence and keywords
SYSTEM IMPLEMENTATION
Key Features
>User selects input type & model
>Shows Prediction, Confidence Score, and Top Keywords
Home screen
SCREEN SHOTS OF EXECUTION
SCREEN SHOTS OF EXECUTION
SCREEN SHOTS OF EXECUTION
CONCLUSION
The system successfully predicts whether a given
news article is real or fake based on its content. It
demonstrates how machine learning can be
applied for real-world problem solving.
FUTURE SCOPE
✅ Integrate deep learning models (e.g., LSTM,
BERT) for better accuracy
✅ Add support for multiple languages
✅ Implement real-time fake news detection from
news feeds or social media
✅ Enable user feedback to improve model learning
✅ Deploy as a mobile app or browser extension
THANK YOU
