Fake news prediction using Logistic regression
Fake news is false or misleading information presented as news. It often has the aim of damaging the reputation of a person or entity, or making money through advertising revenue. However, the term does not have a fixed definition, and has been applied more broadly to include any type of false information, including unintentional and unconscious mechanisms, and also by high-profile individuals to apply to any news unfavourable to their personal perspectives. Hence, there are machine learning based algorithm used to detect the fake news in the online websites. some the research works identify this problem and gives the solution to detect fake news. In this paper, we proposed the Logistic regression based approach to build the model with higher accuracy. For the end product, We uses Django based web application.
Over the past several years, fake news dissemination has become a major problem. Fake news is defined by the New York Times as "made-up stories are written to deceive", and they are published in formats similar to those used by traditional news agencies (Pan, Pavlova, Li, Li, Li and Liu, 2018). Fake news has been identified for contributing to increased political polarization and partisan conflict in recent times. Recent examples included the controversy created during the 2016 presidential campaign for the United States (Pan et al., 2018) and Indian Airstrike in Balakot in 2019. Fake news is a text classification issue with a straight forward proposition (Shu, Sliva, Wang, Tang and Liu, 2017). Building a robust AI framework that can distinguish between "Genuine" news and "Fake" news is required to identify fake news (Pan et al., 2018; Shu et al., 2017). It is a challenging task for social media platforms such as Facebook®, Twitter®, etc. to identify the authentic content (Shu et al., 2017) within the large volume of data posted by the users. There exists a huge risk of posting and publishing such fake and non-authentic content over social media platforms. This research is a positive step towards addressing this critical issue. Figure 1 shows a few examples of fake news which spread over social media platforms during the 2016 U.S. Presidential General Election (Shu et al., 2017). These fake news hampered the public emotionally and spread a negative impact (Persily, 2017) on the society during the 2016 U.S. Presidential General Election. The recent researches (Shu et al., 2017; Pan et al., 2018; Kumar and Shah, 2018) that have been done in the area of detecting fake news are based on both supervised as well as unsupervised methods (Dougherty, Kohavi and Sahami, 1995).
Fake news detection is one of the emerging topics that has caught the attention of researchers across the world in the field of artificial intelligence. Despite receiving significant attention in the research community, fake news detection accuracy has not improve significantly due to insufficient context-specific news data.
In the Proposed method, We uses Logistic regression in order to build the model with better accuracy and able to work with different kinf of dataset.
The dataset for the project is available at the link https://drive.google.com/drive/folders/1GDxv3Jhdx9Ek2LatU6GKG6IJ2-jFUket?usp=sharing
