Constructing a user centered fake news detection
Model by using classification algorithms in machine
learning techniques
Modified Title- Machine Learning Based fake News
Detection Using Regional Convolutional Neural Network
ABSTRACT
• The easy access and exponential growth of the
information available on social media networks has made
it intricate to distinguish between false and true
information.
• The easy dissemination of information by way of
sharing has added to exponential growth of its
falsification.
• Therefore, a RCNN model is proposed to find out the
properties of content that will generate language-driven
features.
• This RCNN model extracts syntactic, grammatical,
sentimental, and readability features of particular news.
• curse of dimensionality problem.
• Therefore, the neural-based sequential learning model is
INTRODUCTION
• Fake news is untrue information presented as news.
• It often has the aim of damaging the reputation of a
person or entity, or making money through
advertising revenue.
• Once common in print, the prevalence of fake news
has increased with the rise of social media, especially
the Facebook News Feed.
Existing system
• Classification of any news item /post / blog into fake
or real one has generated great interest from
researchers around the globe.
• Several research studies have been carried out to find
effect of falsified and fabricated news on masses and
reactions of people upon coming through such news
items.
• In Existing system linguistic model is proposed to
find out the properties of content that will generate
language-driven features.
DISADVANTAGES:
• The easy access and exponential growth of the
information available on social media networks has
made it intricate to distinguish between false and true
information.
• linguistic model Having Less Processing Accuracy
compare to the Proposed system.
• Also it’s a complex and Time Consuming Process.
PROPOSED SYSTEM:
•
• The easy dissemination of information by way of sharing has
added to exponential growth of its falsification.
• The credibility of social media networks is also at stake where the
spreading of fake information is prevalent.
• Thus, it has become a research challenge to automatically check
the information viz a viz its source, content and publisher for
categorizing it as false or true.
• Machine learning has played a vital role in classification of the
information although with some limitations.
• This project uses RCNN approaches in detection of fake and
fabricated news.
• The limitation of such and approaches and improvisation by way
of implementing deep learning is also reviewed
ARCHITECTURE
METHODOLOGY
The proposed method is entirely composed of Artificial
Intelligence approaches, which is critical to accurately classify
between the real and the fake, instead of using algorithms that are
unable to mimic cognitive functions.
The three-part method is a combination between Machine
Learning algorithms that subdivide into supervised learning
techniques, and natural language processing methods.
Although each of these approaches can be solely used to classify
and detect fake news, in order to increase the accuracy and be
applicable to the social media domain, they have been combined
into an integrated algorithm as a method for fake news detection
ALGORITHM
A multilayer perceptron (MLP) Regional Convolutional Neural
Network is an artificial neural network, with an input layer, one
or more hidden layers, and an output layer.
RCNN can be as simple as having each of the three layers;
however, in our experiments we have fine-tuned the model with
various parameters and number of layers to generate an optimum
predicting mode
Advantages
• success in detection of fake news and posts using
various Machine learning approaches.
• everchanging characteristics and features of fake
news in social media networks is posing a challenge
in categorization of fake news
MODULES
Data Collection
Dataset
Data Preparation
Model Selection
Analyze and Prediction
Data Collection
This is the first real step towards the real development of a machine
learning model, collecting data. This is a critical step that will cascade
in how good the model will be, the more and better data that we get,
the better our model will perform.
There are several techniques to collect the data, like web scraping,
manual interventions and etc.
Dataset:
The dataset consists of 3021 individualNews data. There are 7
columns in the dataset, which are described below.
News:
Topic:
Data Preparation:
we will transform the data. By getting rid of missing data and
removing some columns. First we will create a list of column names
that we want to keep or retain.
Next we drop or remove all columns except for the columns that we
want to retain.
Finally we drop or remove the rows that have missing values from
the data set.
Model Selection:
While creating a machine learning model, we need two dataset, one
for training and other for testing.
But now we have only one. So lets split this in two with a ratio of
80:20. We will also divide the dataframe into feature column and label
column.
Analyze and Prediction:
The system will separate words from the given News
● the given words will be stored in .csv file
● the length of the News will be calculated by counting words from
the News file
● check the percentage of keywords matched
● check the percentage of words written compared to that of
minimum length
● check the percentage of News originality score allotted for the
given percentage of keyword matched form the graph.
SOFTWARE
REQUIREMENTS
Front End – Anaconda IDE
Backend – SQL
Language – Python 3.8
HARDWARE REQUIREMENTS:
• RAM : 4GB and Higher
• Processor : Intel i3 and above
• Hard Disk : 500GB:
Minimum
UML DIAGRAM’S USE
CASE
CLASS
DIAGRAM
SEQUENCE
DIAGRAM
ACTIVITY
DIAGRAM
CONCLUTION
The Fake News Detection System is web based and thus can
be accessed through any browsers.
The solution is practical since the objectives of the system
development are achievable and realistic.
The technology to be used is available, this include use of
programming language Python and HTML ,CSS and Django
Framework for WEB based applications.
Although its ML based WEB project most of the ml libraries
are open source and easily accessible
REFERENCE
[1] Viera Maslej Kreˇsˇn´akov´a, Martin Sarnovsk´y, Deep learning methods for Fake
News detection, IEEE Joint 19th International Symposium on Computational Intelligence
and Informatics and 7th IEEE International Conference on Recent Achievements in
Mechatronics, Automation, Computer Sciences and Robotics • November 14-16, 2019
[2] Mulat Getaneh Tiruneh, Amharic WordNet construction Using Word Embedding,
unpublished master’s thesis, Addis Abeba University.
[3] Federico Monti, Fabrizio Frasca, Davide Eynard, Damon Mannion, Fake News
Detection on Social Media using Geometric Deep Learning, Feb, 2019
[4] Md Zobaer Hossainy, Md Ashraful Rahmany, Md Saiful Islam, Sudipta Kar,
BanFakeNews: A Dataset for Detecting Fake News in Bangla, Proceedings of the 12th
Conference on Language Resources and Evaluation (LREC 2020), pages 2862–2871,
Marseille, 11–16 May 2020
[5] Samir Bajaj, Fake news detection using deep learning, Stanford university, 2017
– THANK YOU
