Improving Fake News Detection Using Machine Learning Models
Dr. Pallavi Devendra Tawde , Dipen Limbachia
Abstract
The proliferation of social media has significantly altered the landscape of information dissemination, leading to inconsistencies in online news that can cause considerable confusion and uncertainty for consumers, particularly when they are making critical decisions, such as those related to purchases. This shift has introduced a complex challenge, as the sheer volume and speed of information sharing on platforms like Twitter, Facebook, and Instagram have made it increasingly difficult for individuals to discern the authenticity of the content they encounter. Unfortunately, despite the gravity of this issue, many existing studies have not provided a comprehensive or systematic examination of these inconsistencies, particularly in the context of online reviews and user-generated content.
The spread of fake news and disinformation on social media platforms poses a severe threat to societal stability and harmony. As false information circulates rapidly across these networks, it can influence public opinion, sway political outcomes, and even incite social unrest. The relentless emergence and spread of fake news on social media is a growing concern, as it has the power to mislead entire nations and disrupt the social fabric. This phenomenon has drawn the attention of researchers and professionals who recognize the urgent need to distinguish between fake and real news on these platforms.
Over the years, various studies have been conducted with the aim of developing effective methods to detect fake news on online social media platforms. These studies underscore the critical importance of accurate and timely detection mechanisms, as they play a crucial role in curbing the propagation of false information. The earlier fake news is identified, the easier it becomes to mitigate its impact, thereby protecting the integrity of information shared online.
Keywords: Fake news detection, Machine learning models, Natural language processing (NLP), Deep learning, Data preprocessing, Fake news classification
