final data 20K

The rise of social media platforms such as Twitter has resulted in a significant increase in spam tweets, which may negatively impact both individual and platform providers. In this study, we propose an automated spam detection on Arabian Gulf Dialect Using Machine Learning Techniques to classify tweets as spam or legitimate. This research presents a machine learning-based technique for detecting spam on Twitter in the Arabian Gulf dialect. Support Vector Machines (SVM), Random Forest (RF), and Bidirectional Encoder Representations from Transformers (MarBERT) models have been specifically used for an Arabian Gulf dialect tweet dataset. The accuracy, precision, recall, and F1-score of the three models were used to evaluate their performance. The SVM model outperformed the RF and MarBERT models with 96% accuracy.