NLP and Deep Learning For Fake News Classification in Python

NLP and Deep Learning For Fake News Classification in Python

In this project you will use Python to implement various machine learning methods( RNN, LSTM, GRU) for fake news classification.
explanation image

Videos

Each project comes with 2-5 hours of micro-videos explaining the solution.

ipython image

Code & Dataset

Get access to 102+ solved projects with iPython notebooks and datasets.

project experience

Project Experience

Add project experience to your Linkedin/Github profiles.

Customer Love

Read All Reviews

What will you learn

Understanding the problem statement
Understanding the Sequence problem and their types
Understanding Sequence neural network approach like: RNN, GRU and LSTM
Importing the dataset and importing libraries
Performing basic text cleaning
Perform text preprocessing: Stop word removal, Stemming etc
Text tokenization using keras tokenizer
Sequence data preparation with tokenizer and padding
Train and test split for model validation
Explaining Text vectorization and Word embedding
Build Word embedding layer with Glove
Important parameter before train model
Explaining Sequence model steps
Implementing Simple RNN
Implementing LSTM and GRU
Making Test predictions using the trained model
Comparing Model training and validation loss and performance
Comparing LSTM and GRU performance and computation Time

Project Description

Business Overview

 

What is Fake News?

Fake news is the deliberate presentation of (typically) false or misleading claims as news, where the claims are misleading by design.


How News and digital media evolved?

The news media evolved from newspapers, tabloids, and magazines to a digital form such as online news platforms, blogs, social media feeds, and many news mobile apps. News outlets benefitted from the widespread use of social media/mobile platforms by providing updated news in near real time to its subscribers.

It became easier for consumers to acquire the latest news at their fingertips. So, These digital media platforms become very powerful due to their easy accessibility to the world and ability to allow users to discuss and share ideas and debate over issues such as democracy, education, health, research and history.

However, apart from advantage, false/fake news articles on digital platforms are getting very common and mainly used with a negative intent for their own benefit such as political and financial benefit, creating biased opinions, manipulating mindsets, and spreading absurdity.


How big is this Problem ?

With the rapid adoption of Internet, social media and digital platforms (such as Facebook, Twitter, news portals or any social media), anybody can spread untrue and biased information. It is virtually impossible to prevent Fake News from being created. There has been a rapid increase in the spread of fake news in the last decade, it's not limited to any one domain like politics but covering various other domains such as sports, health, history, entertainment and also science and research. If we take the 2016 US presidential election, there were lots biased and fake news published to influence. Another example could be of COVID-19, we generally come across many misleading/fake news everyday which can have serious consequences and may lead to create panic among people and spread pandemic more rapidly.


What is Solution?

Therefore, It is important and absolutely necessary to identify and differentiate Fake News from real news. One of the ways is to determine by expert and fact check of every news, but this is time consuming and requires skills which can not be shared. Second, we can automate the detection of Fake News by using the techniques of Machine learning and Artificial Intelligence. The Online news content has diverse unstructured format data(such as documents, videos, and audios), here we will concentrate on text format news. With the advancement of and Natural language processing It is possible now that we can identify the deceptive and fake nature of articles or sentences.

There is widespread study and experimentation happening in this area to identify the Fake news for all medium(Video, audio and Text) news.

 

Data Description

In our study we used the Fake news dataset from Kaggle to classify unreliable news articles as Fake news using Deep learning Technique Sequence to Sequence programming.

A full training dataset with the following attributes

  • id : unique id for a news article
  • title: the title of a news article
  • author: author of the news article
  • text : the text of the article; could be incomplete
  • label : a label that marks the article as potentially unreliable
    • 1 : unreliable
    • 0 : reliable

Tech Stack

  • Language : Python
  • Libraries : Scikit-learn , Tensorflow , Keras, Glove, Flask, nltk, pandas, numpy

New Projects

Curriculum For This Mini Project

Business Problem
04m
Data Understanding
04m
Approach : Sequence Problem Neural Network
03m
Simple RNN
03m
Problem with RNN
06m
LSTM
05m
GRU
03m
Steps to Build Many to One Sequence Problem for Text
03m
Data Cleaning
03m
Exploratory Data Analysis
05m
Preparing Training and test datasets
01m
Sequence data transformation
04m
Feature Engineering : Word Embedding
09m
Text based Sequence Neural Network component
04m
Important Hyperparmeters
02m
Building Sequential Neural Network
03m
Training a RNN model
03m
Training LSTM and GRU models
04m
Model Performance comparison: GRU and LSTM
04m
Final Code Walkthrough
08m

Latest Blogs