Paper Key : IRJ************419
Author: Mr. Rohit Gulve,Mr. Yash Wake,Miss. Sangita Zare, Miss. Jagruti Narkhede,Prof. Sanket Chordiya
Date Published: 03 Apr 2024
Abstract
The exponential growth of information on social media platforms has created a complex environment wheredistinguishing between true and false information has become increasingly challenging. The ease of sharingcontent has facilitated the rapid spread of misinformation, jeopardizing the credibility of social media networks.Therefore, there is an urgent need to develop robust methods for automatically verifying the authenticity ofinformation based on its source, content, and publisher. Machine learning techniques have emerged as valuabletools for classifying information as either true or false. However, these approaches are not without limitations. Thispaper provides a comprehensive review of various machine learning methodologies utilized in the detection offake and fabricated news. It critically examines the drawbacks of existing techniques and explores avenues forimprovement through the integration of deep learning methods. By harnessing advancements in data mining andclassification algorithms, this research aims to enhance the accuracy and reliability of fake news detection systems.Key areas of focus include the identification of fake news sources, analysis of content patterns, and evaluation ofpublisher credibility. Through a thorough investigation of these factors, this study seeks to contribute to thedevelopment of more effective strategies for combating the spread of misinformation on social media platforms.Keywords: fake news, machine learning, data mining, classification, svm algorithm.