Fake News Detection System

In today's interconnected world, where the internet is accessible globally, people increasingly rely on various online resources for news. With the widespread use of social media platforms like Facebook and Twitter, news can spread rapidly to millions of users within a very short period. However, this rapid dissemination also contributes to the spread of fake news, which can have significant consequences, such as fostering biased opinions.

This project addresses the issue of fake news detection using a dataset provided by a company. The task involves performing binary classification of online news articles, leveraging concepts from Artificial Intelligence, Natural Language Processing (NLP), and Machine Learning (ML). A decision tree classifier is utilized to distinguish between fake and real news.

Various feature engineering methods for text data, such as the Bag-of-Words model and word embedding techniques, are employed to convert text into feature vectors. These feature vectors are then processed by machine learning algorithms to classify the news as either fake or real. By experimenting with different feature extraction methods and classification algorithms, the project identifies the combination that yields the most accurate results. The optimal feature extraction method and algorithm are then used to predict whether the news is fake or real.

We will classify the news as fake or real using various features and classification algorithms. The combination of feature extraction method and algorithm that produces the best results will be used for prediction. In this project, we will ignore attributes such as the source of the news or whether it was reported online or in print, focusing solely on the content of the news being reported.

Hardware requirement

Processor :Pentium IV 2.4 GHz

Hard Disk: 40 GB and Above.

RAM : 1 GB and Above.

Mouse: Optical Mouse.

Monitor: 14 Colour Monitor.

Keyboard: 101 Keyboards.

Software requirement

Operating System : Windows7

Technology : JSP,Servlet ,HTML,Jscript & CSS

Database : Mysql