Fake News Detection

Project Title

Fake News Detection

Project Area of Specialization Computer ScienceProject Summary

 In this modern era, fake news has become a challenge and many organizations are working on this problem to tackle this problem because people can be easily misguided by fake news. Fake news is used to deceive someone easily or to socialize some author’s personal agenda. Our website saves users time by predicting news article nature and tells users its stance.

         Analyzing and detecting fake news on the internet is one of the hardest problems to be solved. Recently, fake news has been an important topic in the general public and researchers due to online media outlets like social media feeds, blogs, and online newspapers. According to a BBC survey, 79 percent of people are worried about what is fake and real online. The survey of more than 16,000 adults was conducted by Globescan’s chairman Doug Miller said: “These poll findings suggest that the era of ‘fake news’ may be significant in reducing the credibility of online information as Edward Snowden’s 2013 National security Agency (NSA) surveillance revelations were in reducing people’s comfort in expressing their opinions online”. Apple’s stock took a temporary 10-points hit after a false report surfaced on CNN’s report that Steve Jobs had a heart attack.

        Nowadays social media and e-papers are almost accepted as news sources and it leads to an increase in misleading people by click-bait and fake news. It increases distrust even for credible news, politicians, and mainstream media. This problem is more severe in the current era with the wide use of social media and it is easy for anyone to make viral any authors personal agenda or to target someone with opinion-based news or article to target some for the sake of personal agenda, opinion, or gather traffic on a website with false news.

         In 2016 “post-truth” was the word of the year by oxford dictionary because people in this era with the wide use of the internet and social media needs some way to check their readings and tool to avoid or reduce click-bait while surfing web pages what they are going to read is related to its tag or not. Till now news creditably is questionable regardless of some authentic news sources.

Project Objectives

In light of the above incidents, we discover that fake news could have a much more drastic effect even on a country's economy. So to minimize such news to create drastic effects, we have to verify fake news. The purpose of our project is to detect fake news. For this we build a plugin for chrome browser which predicts the nature of the news by using different features and a machine learning model, it checks the content of an article (related or unrelated) by comparing news content with its title. It scrapes down the text and title from a webpage then by using a machine learning model and features it analyze title and content (related or unrelated) with each other. 

Project Implementation Method

In this modern world of social media, fake news spread like wildfire. Like everything, fake news also needs to be in check and balance. For this, we are going to implement the fake news detector which can classify a piece of news as the true or fake one. Fake news detectors can be implemented by training a machine learning model. But common language contains a sense of linguistics and sometimes humor which is very difficult to understand for machines. To overcome this, along with fake news detection we are also proposing a system of news aggregation where visitors of apps can see the news from different sources and contribute in marking news as fake or true and it will also help in differentiating fake news from true news. 

      General steps we will be using for this project will be

• Data Collection

    The data set is the most important need for our project because our algorithm needs it to train itself for prediction.

• Preprocessing the Data

Data preprocessing is crucial in any data mining process as it directly impacts the success rate of the project. ... Data is said to be unclean if it is missing attribute, attribute values, contain noise or outliers, and duplicate or wrong data. The presence of any of these will degrade the quality of the results

• Machine learning

The model will be built using Keras/Tensorflow and data will be fed to the model to train accordingly.

• Web Application

The Web application will be made as a front end so users can properly interact with the system in a user-friendly way. In addition to fake news detection, these are other things that will be on the website

• News Aggregation

• Blog posts

Benefits of the Project

Why ought to you care around whether or not your news is genuine or fake?

1. You deserve the truth.

 You're smart sufficient to create up your claim intellect - as long as you've got the genuine actualities before you. You have got each right to be insulted after you read fake news since you're in the substance being treated like an idiot. 2. Fake news annihilates your validity.

 On the off chance that your contentions are built on terrible data, it'll be much more troublesome for individuals to accept you within the future.

3. Fake news can harm you,  and a lot of other individuals. Purveyors of fake and deluding restorative exhortation like Mercola.com and NaturalNews.com offer assistance sustain myths like HIV and Helps aren't related, or that immunizations cause autism. These sites are heavily visited and their lies are dangerous.

Real news can advantage you. 

In the event that you need to purchase stock in a company, you need to examine precise articles around that company so you'll contribute admirably.

Technical Details of Final Deliverable

To implement this type of software, there are a lot of technicalities involved like Machine Learning, Artificial intelligence and Website development.

In Machine Learning, we need to train a model with thousands of data of both fake and true news. This way machines can learn from the data. After it is trained, it will be able to detect news as fake or true. This training can be done by different Machine Learning algorithms

• Logistics Regression
• SVM(Support Vector Machine)
• Artificial Neural Network(ANN)

To put the cherry on top, We are also making a module along with Fake news detection, where our system can aggregate the news from different websites and visitors of the website can mark news as fake or true according to their opinion. News will be marked as true or false according to the ratio.

Final Deliverable of the Project Software SystemCore Industry MediaOther IndustriesCore Technology Artificial Intelligence(AI)Other TechnologiesSustainable Development Goals Decent Work and Economic GrowthRequired Resources

Item Name	Type	No. of Units	Per Unit Cost (in Rs)	Total (in Rs)
			Total in (Rs)	60000
Latest technology laptops which are compatible with ML	Equipment	3	20000	60000