SEMANTIC ANALYSIS-BASED FAKE NEWS DETECTION USING NLP AND MACHINE LEARNING

The rapid development of digital media and social media networks has increased the dissemination of fake news. Fake news has the ability to deceive readers, shape public opinions, and generate instability in society. It is hard to manually identify fake news due to the vast amount of digital media being posted daily on the internet. This paper proposes a Fake News Detection System that utilizes
Machine Learning and Natural Language Processing techniques for the automatic classification of news articles as fake or genuine. The proposed system utilizes text data processing techniques like
removal of stop words, tokenization, normalization, etc. The processed data is then converted into numerical data using TF-IDF vectorization. A Logistic Regression classifier is used for the detection of fake news. The proposed system provides the results in the form of a prediction along with a confidence score that indicates the likelihood of the news being genuine or fake. The results indicate that the proposed system has high accuracy in detecting fake news articles. This system has the ability to reduce the dissemination of fake news on the internet.