The rapid increase in online platforms and social media sites has transformed information consumption and dissemination, but it has also accelerated to an unparalleled level of propelling the dissemination of false information. Misinformation is a major risk to society as it skews public perceptions, erodes faith in credible media, and impacts political and economic choices. In order to tackle this increasing issue, machine learning has been a great tool for automatically identifying fake news. This study analyzes several machine learning methods, such as Naive Bayes, Random Forest, Logistic Regression, and more complex deep learning models, such as networks with Long Short-Term Memory (LSTM), for the fake news detection job. The training, evaluation of each model, and evaluation of measures are done using labeled dataset. The research illustrates the possibility of artificial intelligence in boosting the veracity of internet content and sheds light on what models work best for usage in the real world to fight fake news.