Scribd
Upload
14 views16 pages

FND PDF

Uploaded by

shreya halaswamy
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
14 views16 pages

FND PDF

Uploaded by

shreya halaswamy
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 16

Sri Shyla Educational Trust (R), Bheemasamudra

GM INSTITUTE OF TECHNOLOGY, DAVANGERE


(Affiliated to VTU, Belagavi, Approved by AICTE – New Delhi & Govt. of Karnataka)

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING

Internship presentation on: Fake news detection


GUIDED BY: PRESENTED BY:
Mrs. Sandhya R Savanur Rajani K 4GM21CS076
Assisstant professor Sharadhi S G 4GM21CS097
Shreya N M H 4GM21CS100
Sushmitha V N 4GM21CS112
CONTENTS
1. Company profile

2. Introduction

3. Tasks performed

4. Problem statement

5. Objective

6. Proposed solution

7. Design/Methodology

8. Implementation

9. Results

10. Conclusion

11. References
COMPANY PROFILE
SIRINTEL TECHNOLOGIES:

➢ HR DIRECTOR: MAMATA T

➢ TECHNICAL HEAD: SHIVALI S

➢ Sirintel is a Information Technology (IT) Service provider which delivers the complete solution for
the entire software necessities with the assured quality.
➢ It is a leading firm providing technological solutions to various students across the State of
Karnataka to enrich their knowledge with practical experience and live training through various
projects.
➢ The vision of Sirintel Technologies is to involve its students in never-ending Engineering Research
and make them excel in Quality Education.
➢ They gained the local, national and international clients due to the dedicate services since 2015.
INTRODUCTION
➢ In today's era of technology, fake news has become a
rampant issue.
➢ Fake news on different platforms is spreading widely
for personal or societal gain and is a matter of concern.
➢ Here's a solution to use machine learning to detect fake
news.
TASKS PERFORMED

WEEK 1 Basics of Python and data structures in Python

WEEK 2 Ethical hacking

WEEK 3 Creating GUI in Python


PROBLEM STATEMENT

Prevalence of Fake News Difficulty in Detection


The world is plagued by the spread of It's not easy to identify fake news without
disinformation, propaganda, and misleading wasting time and effort.
information.

Impact on Society Urgent Need for Solution


Exposure to fake news can harm critical The increasing amount of unverified
thinking and decision-making skills. information requires immediate attention to
address the issue.
OBJECTIVES
To detect fake news effectively to avoid defamation of individuals.

Determines the accuracy of the "Fake news detector".


PROPOSED SOLUTION
➢ Passive Aggressive Classifier algorithm is implemented to detect fake news. Fake news dataset is
provided where the task is to train a model to detect fake news.

➢ Passive Aggressive Classifier is a classification algorithm that falls under the category of
online learning in machine learning.
➢ It is an online learning algorithm where you train a system incrementally by feeding it instances
sequentially, individually or in small groups called mini-batches.
➢ It remains passive for correct predictions and responds aggressively to incorrect predictions.
DESIGN / METHODOLOGY
Data Collection The dataset is loaded form a CSV file named
"news.csv". It contains labelled news articles.

Data Preprocessing After loading the dataset, the code prepares the data
for training. It splits the dataset into 2 parts: training
set and testing set.

Feature Extraction To convert the textual data into a numerical format


suitable for machine learning, the code uses the Term
Frequency-Inverse Document Frequency (TF-IDF).
Model Training Training the machine learning model using Passive
Aggressive Classifier (PAC) .

Model Evaluation Evaluating the accuracy of the model using


Confusion Matrix.
Confusion matrix It is a table with 4 different combinations of predicted
and actual values.
IMPLEMENTATION
RESULTS
The below snapshot is the output window showing 92.74% accuracy of the fake news detector.
Conclusion
➢ With the proliferation of social media and the rapid dissemination of information, it has become
increasingly challenging to discern genuine news from fabricated stories.

➢ By empowering users to verify news stories before sharing or believing them, we can collectively
reduce the spread of fake news and combat the harmful effects it has on individuals and
communities.

➢ The proposed system is effective and efficient in detecting fake news using machine learning
algorithms and the Confusion Matrix concept. It can be deployed and used by news agencies, social
media, and online platforms to detect fake news and enhance their credibility.
REFERENCES
➢ Lazer, David M. J., et al. "The Science of Fake News." Science, vol. 359, no. 6380, 2018, pp. 1094-1096.

➢ Wang, William Yang, et al. "Liar, Liar Pants on Fire: A New Benchmark Dataset for Fake News
Detection." Proceedings of the 55th Annual Meeting of the Association for Computational
Linguistics, 2017, pp. 422-426.

➢ Rubin, Victoria L., et al. "Deception Detection for News: Three Types of Fakes." Proceedings of the
Association for Information Science and Technology, vol. 52, no. 1, 2015, pp. 1-4.
THANK YOU

You might also like