HETEROGENEOUS ENSEMBLE STRUCTURE BASED UNIVERSAL SPAM PROFILE DETECTION SYSTEM FOR ONLINE SOCIAL MEDIA NETWORKS.

The exponential rise in internet technology and online social media networks have revitalized human-being to connect and socialize globally irrespective of geographical and any demographic boundaries. Additionally, it has revitalized business communities to reach target audiences through social media networks. However, as parallel adverse up-surge the ever-increasing presence of malicious users or spam has altered predominant intend of such social media network by propagating biased contents, malicious contents and fraud acts. Avoiding and neutralizing such malefic users on social media network has remained a critical challenge due to gigantically large size and user's diversity such as Facebook, Twitter, and LinkedIn etc. Though exploiting certain user's behavior and content types can help identifying malicious users, majority of the existing methods are limited due to confined parametric assessment, and inferior classification approaches. With intend to provide spam profile detection system in this paper a novel heterogeneous ensemble-based method is developed. The proposed model exploits user profile features, user's activity features, location features and content features to perform spam user profile detection. To ensure optimality of computational significances, we applied multi-phased feature selection method employing WilcoxonRank Sum test, Significant Predictor test, and Pearson Correlation test, which assured retaining optimal feature sets for further classification. Subsequently, applying an array of machine learning methods, including Logistic regression, decision tree, Support Vector Machine variants with Linear, Polynomial and RBF kernels, Least Square SVM with linear, polynomial and RBF kernels, ANN with different kernels, etc we constituted a robust ensemble model for spam user profile classification. Simulations revealed that the proposed ensemble classification model achieves accuracy and F-score higher than 98%, which is the highest amongst major works done so far. It affirms suitability and robustness of the proposed model for real time spam profile detection and classification on social media platforms. [ABSTRACT FROM AUTHOR]