Fake News Detection

fake news detection

In Python (NLP)

Group members: Bhavishya Dharmani Aniket Surve Lokesh Chachad

Introduction

• As an increasing amount of our lives is spent interacting online through social media platforms, more and more people tend to hunt out and consume news from social media instead of traditional news organizations.
• However, because it's inexpensive to supply news online and far faster and easier to propagate through social media, large volumes of false news.
• To assist mitigate the negative effects caused by fake news (both to profit the general public and therefore the news ecosystem), It's crucial that we build up methods to automatically detect fake news.

Generales

Specific

problem statement

• The purpose of this proposed project is to assist mitigate the negative effects caused by fake news detect it by using Machine learning and Natural Language Processing and classify it into REAL or FAKE news.
• Also provide the Sentiment of the news that is being spread.

Generales

Specific

literature survey

• Fake News Detection Using Machine Learning approaches: A systematic Review [ Syed Ishfaq Manzoor,Dr Jimmy Singla,Nikita]

• Fake News Detection using Machine Learning [Jasmine Shaikh,Rupali Patil]
• Fake News Detection using Machine Learning [Nihel Fatima Baarir,Abdelhamid Djeffal]
• Identification of Fake News Using Machine Learning [Rahul R Mandical,Shivakumar N]

• Detecting Fake News Using Machine Learning Algorithms [K J Manikanta,R.Sumathi]
• A Tool for Fake News Detection [Bashar Al Asaad]

Data Split (Train & Test)

Pre- Processing

Feature Extraction

DATASET

User Input

Training the classifier

Classification Model

TRUE / FALSE

dataset used for training model

Fake and real news dataset from Kaggle:

Generales

Specific

Pre-processing

Data pre-processing can be done by removing:

Generales

Specific

• Lexical Analysis
• URL Removal
• Tokenization
• Stop Word Removal

machine learning models

• Naive Bayes
• Support Vector Machine (SVM)
• Passive Aggressive Classifier

Generales

Specific

Confusion Matrix

Naïve Bayes

PassiveAggressive

SVM Classifier

Generales

Specific

Performance parameters

Text Summarization are of two types:

Generales

Sentiment Analysis of the news

• For Sentiment analysis in our project, we will use vaderSentiment.
• VADER (Valence Aware Dictionary and sEntiment Reasoner) is a lexicon and rule-based sentiment analysis tool that is specifically attuned to sentiments expressed in social media.
• It is fully open-source.
• It incorporate word-order sensitive relationships between terms instead of bag of words model.

Conclusion

• We present a novel method to detect real and fake news via using the technology NLP.
• This work establishes the proof of working principle and sets direction for future development into a fully learned and automated method for detection of fake news.
• We look forward to newer methods emerging from the research community leading to an improved experience.

Thanks for your attention!