Detecting Fake Social Media Profiles Using the Majority Voting Approach

INTRODUCTION: The rise of social media platforms has brought about a concerning surge in the creation of fraudulent user profiles, with intentions ranging from spreading false information and perpetrating fraud to engaging in cyberbullying. The detection of these deceptive profiles has emerged as a critical imperative to safeguard the trustworthiness and security of online communities. OBJECTIVES: This paper focused on the detection and identification of fake social media profiles. METHODS: This paper introduces an innovative approach for discerning and categorizing counterfeit social media profiles by leveraging the majority voting approach. The proposed methodology integrates a range of machine learning algorithms, including Decision Trees, XGBoost, Random Forest, Extra Trees, Logistic Regression, AdaBoost and K-Nearest Neighbors each tailored to capture distinct facets of user behavior and profile attributes. This amalgamation of diverse methods results in an ensemble of classifiers, which are subsequently subjected to a majority voting mechanism to render a conclusive judgment regarding the legitimacy of a given social media profile. RESULTS: We conducted thorough experiments using a dataset containing both legitimate and fake social media profiles to determine the efficiency of our methodology. Our findings substantiate that the Majority Voting Technique surpasses individual classifiers, attaining an accuracy rate of 99.12%, a precision rate of 99.12%, a recall rate of 99.12%, and an F1-score of 99.12%. CONCLUSION: The results show that the majority vote method is reliable for detecting and recognising fake social media profiles.