Fake Account Detection on Social Media Using Machine Learning

Online social media is the dominant force in today’s world in many ways, and its user base is expanding daily. Social media usage is rapidly increasing. The main advantage is the ease and effectiveness with which we may communicate with others through online social media. This created a new potential attack vector, including a fake identity, misleading information, and so forth. A new study indicates that there are far more accounts among social media users than there are users themselves. Online social network providers find it challenging to identify these fraudulent accounts. Recognizing these fraudulent accounts is crucial since social media is overflowing with advertisements, misleading information, and other kinds of content. We provide a technique for identifying fraudulent accounts using a dataset of online social media. Instead of using normal machine learning classifiers, we used boosting techniques to increase the accuracy of the usual methodology. This approach has led to a significant increase in accuracy by strengthening poor learners. This research will compare the accuracy of the Gradient Boosting Classifier and the Xgboost Classifier. Xgboost did a fantastic job in comparison to the earlier work.