A novel Machine learning technique for fake smart watches advertisement detection
Anum Zaheer, Sidra Tahir, Mamoona Humayun, Maram Fahhad Almufareh, N. Z. Jhanjhi
Abstract
Fake social media advertisements for items such as smart watches and other types of media are common and a major subject of concern due to their potential to cause considerable social and national harm. This paper examines the research on fake advertisement detection and investigates machine learning models to select the best, in order to create a model of a product with supervised machine learning algorithm, that can classify fake advertisement as true or false, by using tools like python scikit-learn, NLP for textual analysis, and CNN, LSTM, RNN deep learning models for image analysis. We divided our data into 30 and 70 ratios. We trained our algorithm using 70% of the data. The remaining 30% of the data was examined using assessment measures such as accuracy, recall, and fscore. Out of 404 total advertisements, our algorithm identified 372 genuine ads and 32 fake ads.