A Study on Identification of Fake News Using Real-time Analytics

Main Article Content

Yashaswini N., Srinath G .S., Nagaraj A., Sudharshan S., Sayed Faizal, Rajkumar N.

Abstract

Consistent with the expansion of the internet entertainment sector, false information is proliferating. It is progressively emerging as one of the most pressing issues of our time. Those who seek to tarnish the reputation of an organization will spread false information about it. The principal aim of this research is to develop a methodology utilizing Machine Learning to contrast the linguistic attributes of authentic and fabricated news. The primary objective of this paper is to develop a machine learning-based system capable of differentiating between accurate and inaccurate news language plans. We present a compilation of Machine Learning models designed to identify deception in this study. These algorithms possess the capability to discern genuine news articles from fabricated ones, despite operating in an environment that is perpetually evolving. Prominent techniques investigated in this study include logistic regression, a TFIDF vectorizer (term frequency-inverse document frequency), and a random forest classifier. As machine learning models apply to a vast array of unstructured data, they are an excellent option for conducting realistic sentiment analysis. Fake news is a difficult issue currently. Detecting fake news is significant on the grounds it assists us in safeguarding ourselves from being misdirected. This paper lets us know how to deduct fake news, where we can assist with making the world more educated and secure spot. Today, fake news is a problematic issue to address. Identifying false news is crucial because it helps us avoid being misinformed. This paper helps us to identify false news so that we can contribute to making the world a more educated and secure place. This paper aimed to enhance a fake news deduction. By utilizing modern technology, the study explored innovative approaches towards deducting fake news.

Article Details

Section
Articles