Machine learning algorithm-based spam detection in social networks

• Published in: Social network analysis and mining 2023-08, Vol.13 (1), p.104
• Main Authors: Sumathi, M, Raja, S. P
• Format: Article
• Language: English
• Subjects: Accuracy; Algorithms; Artificial intelligence; Business metrics; Classification; Classifiers; Cybercrime; Datasets; Decision trees; Deep learning; Dictionaries; Electronic mail systems; Flexibility; Literature reviews; Machine learning; Neural networks; Performance evaluation; Recall; Social media; Social networks; Statistical analysis; Support vector machines
• ISSN: 1869-5450; 1869-5469
• DOI: 10.1007/s13278-023-01108-6

Many social media (SM) platforms have emerged as a result of the online social network’s (OSN) rapid expansion. SM has become important in day-to-day life, and spammers have turned their attention to SM. Spam detection (SD) is done in two different ways, such as machine learning (ML) and expert-based detection. The expert-based detection technique’s accuracy depends on expert knowledge, and it takes huge time to detect the spams. Thus, ML-based spam detection is preferred in OSN. Spam identification on social networks is a difficult operation involving a variety of factors, and spam and ham have resulted in an imbalanced data distribution, which gives flexibility to spammers for corrupting our devices. SD based on ML algorithms like logistic regression (LR), K-nearest neighbor (KNN), decision trees (DT), random forest (RF), support vector machine (SVM) and eXtreme gradient boosting (XGB), voting classifier (VC) and extra tree classifier (ETC) are used to design the address balance and to attain high assessment accuracy in an imbalanced datasets. ETC method minimizes the bias through the original sampling process. For reducing processing complexity, the ETC method uses a smaller size constant factor instead of a larger one. Thus, the ETC technique produces better data splitting than DT and RF techniques. Text is vectorized by vectorizers, and all the relative results are stored in it. The VC is an ensemble method that integrates predictions form several methods to forecast an output class depending on which predictions have the highest probability. The multi-class results are aggregated and forecast for the majority voted class. The experimental result shows that, as compared to KN, NB, ETC, RF, SVC, LR, XGB and DT, the proposed VC provides a higher classification accuracy rate of 97.96%, 97.56% of precision, 89.95% of recall and 91.96% of F1-measures. Similarly, ETC provides 97.77% accuracy, 98.31% of precision, 84.78% of recall and 91.05% of F1-measures. Compared to conventional ML algorithms, VC and ETC provide higher accuracy, precision, recall and F1-measures. Thus, ETC and VC are preferable for spam detection. The website has been designed to detect messages as spam or not.