ABSTRACTIn the digital age, social media has become a primary source of news and information for millions of users worldwide. However, the rapid and widespread dissemination of information on these platforms has also led to the rise of fake news—misleading or false content intended to deceive. This study explores the analysis and detection of fake news on social media using machine learning and natural language processing (NLP) techniques. The objective is to identify patterns, linguistic features, and dissemination behaviors that distinguish fake news from genuine content. Various algorithms such as Naive Bayes, Support Vector Machines (SVM), and deep learning models are employed and evaluated for their effectiveness in classification tasks. The study also examines the role of user behavior, metadata, and network structure in improving detection accuracy. By developing automated systems for fake news detection, this research aims to contribute to the integrity and reliability of online information and promote responsible consumption of news on social media platforms. Fake news has become a serious issue on social media platforms, where false or misleading information spreads quickly and influences public opinion. Analyzing fake news involves using techniques like machine learning and natural language processing to detect and classify unreliable content. By studying the text, user behavior, and how the news spreads, researchers can build models to automatically identify fake news. This helps in reducing misinformation and promoting accurate information sharing online. Keywords: N-grams & bag-of-words, TF-IDF scores ,Emotional or sensational language, pronoun counts, readability.