Misguided news that is presented as false news or that intentionally confounds the truth and the false for personal gain harms society and occasionally individual people. The spread of fake news on social media and other platforms is a serious worry because it has the potential to have a negative influence on society and the country. Smartphone users prefer to read the news on social media due to social media's ease of access. But we cannot be sure how reliable the source is. Traditional fact checking has become impractical due to changes in publishing because of the wave of content producers and other factors in the matter of online news or news on social media. These kinds of unusual circumstances might occasionally have an impact on how people feel and what they believe. The need to identify bogus news led to the creation of this study. In this work, fake news identification is accomplished using ML algorithms Logistic Regression (LR) Decision Tree (DT), Random Forest (RF), Extreme Gradient Boosting (XGB), Gradient Boosting (GB), Multinomial Naive Bayes (MNB) and K Nearest Neighbors (KNN). We have determined the precision, recall, F-measure, accuracy for each of the classifiers. To be more specific, we employed a total of 44898 distinct news pieces from a dataset of authentic and fake news to train a ML model using Count vectorizer and TF-IDF as feature extraction approaches, with the highest performing model LR achieving an accuracy of 93.86%.