The majority of people now use social networking sites as part of their everyday lives. Every day, a vast number of people build profiles on social networking sites and connect with others, regardless of their place or time. Users of social networking sites not only profit from them, but they also face security concerns about their personal details. To assess who is promoting threats in social networks, we must first identify the users’ social network profiles. It is necessary to differentiate between genuine and false accounts on social media based on the classification. Detecting false accounts on social media has historically focused on a number of classification methods. However, it is possible to boost the accuracy of fake profile identification in social media. Machine learning and natural language processing (NLP) technologies are used in the proposed work to increase the percentage of fake profile prediction. The Support Vector Machine (SVM) and the Naive Bayes algorithm are the two algorithms used in classification provides better results.